Merge branch 'master' of https://git.wmi.amu.edu.pl/s406917/VisionScore into VIS-48

.gitignore

@@ -0,0 +1 @@
+files/output/*

win_venv/main.py

@@ -1,6 +1,6 @@
 #import tkinter as tk
 import sys
-import os
+import os, subprocess
 import shutil
 from datetime import datetime
 import time
@@ -18,9 +18,9 @@ LIB_VIS = 1
 
 
 def files(path):
-    for file in os.listdir(path):
-        if os.path.isfile(os.path.join(path, file)):
-            yield file
+    for subdir, dirs, files_list in os.walk(path): 
+        for file in files_list:
+            yield os.path.join(subdir, file)
 
 def save_input(oldpath):
     # make timestampt the filename, so it wouln't overwrite
@@ -55,7 +55,11 @@ class LibraryTableButtons(QWidget):
                 table.fillTable(type)
         
         def analyzeFile():
-            # todo: run script detect.py --source ../files/input/file.mp4
+            cmd = "py detect.py --source {} --view-img".format(str(file))
+
+            popen = subprocess.Popen(cmd, cwd="../yolov5/", stdout=subprocess.PIPE)
+            popen.wait()
+            # todo: display gif/spinning wheel
             pass
 
         layout = QHBoxLayout()
@@ -116,8 +120,9 @@ class LibraryTable(QTableWidget):
 
             dates = []
             names = [] 
+
             for index, file in enumerate(files(filePath)):
-                dates.append(QTableWidgetItem(str(datetime.fromtimestamp(os.path.getmtime(filePath + '/' + file)))))
+                dates.append(QTableWidgetItem(str(datetime.fromtimestamp(os.path.getmtime(file)))))
                 names.append(QTableWidgetItem(str(file)))
 
             self.setRowCount(len(dates))
@@ -125,44 +130,17 @@ class LibraryTable(QTableWidget):
             for index, date in enumerate(dates):
                 self.setItem(index,0,date)
                 self.setItem(index,1,names[index])
-                self.setCellWidget(index,2,LibraryTableButtons(filePath + '\\' + names[index].text(), self, type))
+                self.setCellWidget(index,2,LibraryTableButtons(names[index].text(), self, type))
 
 
 class formatHelp(QLabel):
 
     def __init__(self, parent=None):
         QLabel.__init__(self)
-        help_text = '''
-        VisionScore to program służący do generowania analizy nagrań lub zdjęć z meczów piłkarskich.
-        
-        By wygenerować taką analizę, należy postępować według następujących kroków:
-        
-        1. Wgraj plik z plikiem do przeanalizowania
-            File -> Upload new file
-        2. Po wgraniu pliku pojawi się on w 
-            Library -> Input files
-        # 3. By wygenerować analizę należy kliknąć przycisk
-            Analyze
-        znajdujący się obok wgranego pliku. Analizę można wygenerować także do uprzednio wgranych plików.
-        4. Po wygenerowaniu, analiza znajdować się będzie w 
-            Library -> Vizusalizations
-        możesz tam także zobaczyć wszystkie poprzednio wygenerowane analizy.
-        
-        Każdy plik źródłowy lub wygenerowaną analizę możesz w każdym momencie podejrzeć klikając
-            View
-        obok pliku znajdującego się w bibliotekach. Plik możesz też w każdym momencie usunąć klikając
-            Delete
-        obok odpowiedniego pliku.
-        
-        
-        Zakończ działanie aplikacji klikąc
-            File -> Exit
-        używając skrótu klawiszowego Ctrl+Q lub bo prostu zamykając okienko aplikacji.
-        
-        
-        Kontakt: mikbed@st.amu.edu.pl
-            '''
+        with open('static/help.txt', 'r', encoding='utf-8') as file:
+            help_text = file.read().replace('\n', '')
         self.setText(help_text)
+        self.setStyleSheet("padding-left: 20px; padding-right: 20px; padding-top: 10px; padding-bottom: 10px; font-size:32px;")
         self.adjustSize()
 
 
@@ -241,7 +219,7 @@ class MainWindow(QMainWindow):
         helpAct.triggered.connect(self.showHelp)
         menuBar.addAction(helpAct)
         
-        self.show()
+        self.showMaximized()
 
 
 def main():

win_venv/static/help.txt

@@ -0,0 +1 @@
+<p>VisionScore to program służący do generowania analizy nagrań lub zdjęć z mecz&oacute;w piłkarskich.<br /><br />By wygenerować taką analizę, należy postępować według następujących krok&oacute;w:<br /><br />1. Wgraj plik z plikiem do przeanalizowania<br /><em>File -&gt; Upload new file</em><br />2. Po wgraniu pliku pojawi się on w <br /><em>Library -&gt; Input files</em><br /> 3. By wygenerować analizę należy kliknąć przycisk<br /><em>Analyze</em><br />znajdujący się obok wgranego pliku. Analizę można wygenerować także do uprzednio wgranych plik&oacute;w.<br />4. Po wygenerowaniu, analiza znajdować się będzie w <br /><em>Library -&gt; Vizusalizations</em><br />możesz tam także zobaczyć wszystkie poprzednio wygenerowane analizy.<br /><br />Każdy plik źr&oacute;dłowy lub wygenerowaną analizę możesz w każdym momencie podejrzeć klikając<br /><em>View</em><br />obok pliku znajdującego się w bibliotekach. Plik możesz też w każdym momencie usunąć klikając<br /><em>Delete</em><br />obok odpowiedniego pliku.<br /><br /><br />Zakończ działanie aplikacji klikąc<br /><em>File -&gt; Exit</em><br />używając skr&oacute;tu klawiszowego Ctrl+Q lub bo prostu zamykając okienko aplikacji.<br /><br /><br /><strong>Kontakt: mikbed@st.amu.edu.pl</strong></p>

yolov5/.gitignore

@@ -0,0 +1,252 @@
+# Repo-specific GitIgnore ----------------------------------------------------------------------------------------------
+*.jpg
+*.jpeg
+*.png
+*.bmp
+*.tif
+*.tiff
+*.heic
+*.JPG
+*.JPEG
+*.PNG
+*.BMP
+*.TIF
+*.TIFF
+*.HEIC
+*.mp4
+*.mov
+*.MOV
+*.avi
+*.data
+*.json
+
+*.cfg
+!cfg/yolov3*.cfg
+
+storage.googleapis.com
+runs/*
+data/*
+!data/images/zidane.jpg
+!data/images/bus.jpg
+!data/coco.names
+!data/coco_paper.names
+!data/coco.data
+!data/coco_*.data
+!data/coco_*.txt
+!data/trainvalno5k.shapes
+!data/*.sh
+
+pycocotools/*
+results*.txt
+gcp_test*.sh
+
+# Datasets -------------------------------------------------------------------------------------------------------------
+coco/
+coco128/
+VOC/
+
+# MATLAB GitIgnore -----------------------------------------------------------------------------------------------------
+*.m~
+*.mat
+!targets*.mat
+
+# Neural Network weights -----------------------------------------------------------------------------------------------
+*.weights
+*.pt
+*.onnx
+*.mlmodel
+*.torchscript
+darknet53.conv.74
+yolov3-tiny.conv.15
+
+# GitHub Python GitIgnore ----------------------------------------------------------------------------------------------
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+wandb/
+.installed.cfg
+*.egg
+
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv*
+venv*/
+ENV*/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+
+# https://github.com/github/gitignore/blob/master/Global/macOS.gitignore -----------------------------------------------
+
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+Icon?
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+
+# https://github.com/github/gitignore/blob/master/Global/JetBrains.gitignore
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff:
+.idea/*
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/dictionaries
+.html  # Bokeh Plots
+.pg  # TensorFlow Frozen Graphs
+.avi # videos
+
+# Sensitive or high-churn files:
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+
+# Gradle:
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# CMake
+cmake-build-debug/
+cmake-build-release/
+
+# Mongo Explorer plugin:
+.idea/**/mongoSettings.xml
+
+## File-based project format:
+*.iws
+
+## Plugin-specific files:
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties

yolov5/Dockerfile

@@ -0,0 +1,55 @@
+# Start FROM Nvidia PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch
+FROM nvcr.io/nvidia/pytorch:20.12-py3
+
+# Install linux packages
+RUN apt update && apt install -y screen libgl1-mesa-glx
+
+# Install python dependencies
+RUN pip install --upgrade pip
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+RUN pip install gsutil
+
+# Create working directory
+RUN mkdir -p /usr/src/app
+WORKDIR /usr/src/app
+
+# Copy contents
+COPY . /usr/src/app
+
+# Copy weights
+#RUN python3 -c "from models import *; \
+#attempt_download('weights/yolov5s.pt'); \
+#attempt_download('weights/yolov5m.pt'); \
+#attempt_download('weights/yolov5l.pt')"
+
+
+# ---------------------------------------------------  Extras Below  ---------------------------------------------------
+
+# Build and Push
+# t=ultralytics/yolov5:latest && sudo docker build -t $t . && sudo docker push $t
+# for v in {300..303}; do t=ultralytics/coco:v$v && sudo docker build -t $t . && sudo docker push $t; done
+
+# Pull and Run
+# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t
+
+# Pull and Run with local directory access
+# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/coco:/usr/src/coco $t
+
+# Kill all
+# sudo docker kill $(sudo docker ps -q)
+
+# Kill all image-based
+# sudo docker kill $(sudo docker ps -a -q --filter ancestor=ultralytics/yolov5:latest)
+
+# Bash into running container
+# sudo docker container exec -it ba65811811ab bash
+
+# Bash into stopped container
+# sudo docker commit 092b16b25c5b usr/resume && sudo docker run -it --gpus all --ipc=host -v "$(pwd)"/coco:/usr/src/coco --entrypoint=sh usr/resume
+
+# Send weights to GCP
+# python -c "from utils.general import *; strip_optimizer('runs/train/exp0_*/weights/best.pt', 'tmp.pt')" && gsutil cp tmp.pt gs://*.pt
+
+# Clean up
+# docker system prune -a --volumes

yolov5/deep_sort_pytorch/.gitignore

@@ -0,0 +1,13 @@
+# Folders
+__pycache__/
+build/
+*.egg-info
+
+
+# Files
+*.weights
+*.t7
+*.mp4
+*.avi
+*.so
+*.txt

yolov5/deep_sort_pytorch/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2020 Ziqiang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

yolov5/deep_sort_pytorch/README.md

@@ -0,0 +1,137 @@
+# Deep Sort with PyTorch
+
+![](demo/demo.gif)
+
+## Update(1-1-2020)
+Changes
+- fix bugs
+- refactor code
+- accerate detection by adding nms on gpu
+
+## Latest Update(07-22)
+Changes
+- bug fix (Thanks @JieChen91 and @yingsen1 for bug reporting).  
+- using batch for feature extracting for each frame, which lead to a small speed up.  
+- code improvement.
+
+Futher improvement direction  
+- Train detector on specific dataset rather than the official one.
+- Retrain REID model on pedestrain dataset for better performance.
+- Replace YOLOv3 detector with advanced ones.
+
+**Any contributions to this repository is welcome!**
+
+
+## Introduction
+This is an implement of MOT tracking algorithm deep sort. Deep sort is basicly the same with sort but added a CNN model to extract features in image of human part bounded by a detector. This CNN model is indeed a RE-ID model and the detector used in [PAPER](https://arxiv.org/abs/1703.07402) is FasterRCNN , and the original source code is [HERE](https://github.com/nwojke/deep_sort).  
+However in original code, the CNN model is implemented with tensorflow, which I'm not familier with. SO I re-implemented the CNN feature extraction model with PyTorch, and changed the CNN model a little bit. Also, I use **YOLOv3** to generate bboxes instead of FasterRCNN.
+
+## Dependencies
+- python 3 (python2 not sure)
+- numpy
+- scipy
+- opencv-python
+- sklearn
+- torch >= 0.4
+- torchvision >= 0.1
+- pillow
+- vizer
+- edict
+
+## Quick Start
+0. Check all dependencies installed
+```bash
+pip install -r requirements.txt
+```
+for user in china, you can specify pypi source to accelerate install like:
+```bash
+pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+```
+
+1. Clone this repository
+```
+git clone git@github.com:ZQPei/deep_sort_pytorch.git
+```
+
+2. Download YOLOv3 parameters
+```
+cd detector/YOLOv3/weight/
+wget https://pjreddie.com/media/files/yolov3.weights
+wget https://pjreddie.com/media/files/yolov3-tiny.weights
+cd ../../../
+```
+
+3. Download deepsort parameters ckpt.t7
+```
+cd deep_sort/deep/checkpoint
+# download ckpt.t7 from
+https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6 to this folder
+cd ../../../
+```  
+
+4. Compile nms module
+```bash
+cd detector/YOLOv3/nms
+sh build.sh
+cd ../../..
+```
+
+Notice:
+If compiling failed, the simplist way is to **Upgrade your pytorch >= 1.1 and torchvision >= 0.3" and you can avoid the troublesome compiling problems which are most likely caused by either `gcc version too low` or `libraries missing`.
+
+5. Run demo
+```
+usage: python yolov3_deepsort.py VIDEO_PATH
+                                [--help]
+                                [--frame_interval FRAME_INTERVAL]
+                                [--config_detection CONFIG_DETECTION]
+                                [--config_deepsort CONFIG_DEEPSORT]
+                                [--display]
+                                [--display_width DISPLAY_WIDTH]
+                                [--display_height DISPLAY_HEIGHT]
+                                [--save_path SAVE_PATH]          
+                                [--cpu]          
+
+# yolov3 + deepsort
+python yolov3_deepsort.py [VIDEO_PATH]
+
+# yolov3_tiny + deepsort
+python yolov3_deepsort.py [VIDEO_PATH] --config_detection ./configs/yolov3_tiny.yaml
+
+# yolov3 + deepsort on webcam
+python3 yolov3_deepsort.py /dev/video0 --camera 0
+
+# yolov3_tiny + deepsort on webcam
+python3 yolov3_deepsort.py /dev/video0 --config_detection ./configs/yolov3_tiny.yaml --camera 0
+```
+Use `--display` to enable display.  
+Results will be saved to `./output/results.avi` and `./output/results.txt`.
+
+All files above can also be accessed from BaiduDisk!  
+linker：[BaiduDisk](https://pan.baidu.com/s/1YJ1iPpdFTlUyLFoonYvozg)
+passwd：fbuw
+
+## Training the RE-ID model
+The original model used in paper is in original_model.py, and its parameter here [original_ckpt.t7](https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6).  
+
+To train the model, first you need download [Market1501](http://www.liangzheng.com.cn/Project/project_reid.html) dataset or [Mars](http://www.liangzheng.com.cn/Project/project_mars.html) dataset.  
+
+Then you can try [train.py](deep_sort/deep/train.py) to train your own parameter and evaluate it using [test.py](deep_sort/deep/test.py) and [evaluate.py](deep_sort/deep/evalute.py).
+![train.jpg](deep_sort/deep/train.jpg)
+
+## Demo videos and images
+[demo.avi](https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6)
+[demo2.avi](https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6)
+
+![1.jpg](demo/1.jpg)
+![2.jpg](demo/2.jpg)
+
+
+## References
+- paper: [Simple Online and Realtime Tracking with a Deep Association Metric](https://arxiv.org/abs/1703.07402)
+
+- code: [nwojke/deep_sort](https://github.com/nwojke/deep_sort)
+
+- paper: [YOLOv3](https://pjreddie.com/media/files/papers/YOLOv3.pdf)
+
+- code: [Joseph Redmon/yolov3](https://pjreddie.com/darknet/yolo/)

yolov5/deep_sort_pytorch/configs/deep_sort.yaml

@@ -0,0 +1,10 @@
+DEEPSORT:
+  REID_CKPT: "deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7"
+  MAX_DIST: 0.3
+  MIN_CONFIDENCE: 0.3
+  NMS_MAX_OVERLAP: 0.5
+  MAX_IOU_DISTANCE: 0.7
+  MAX_AGE: 70
+  N_INIT: 3
+  NN_BUDGET: 100
+  

yolov5/deep_sort_pytorch/deep_sort/README.md

@@ -0,0 +1,3 @@
+# Deep Sort 
+
+This is the implemention of deep sort with pytorch.

yolov5/deep_sort_pytorch/deep_sort/__init__.py

@@ -0,0 +1,21 @@
+from .deep_sort import DeepSort
+
+
+__all__ = ['DeepSort', 'build_tracker']
+
+
+def build_tracker(cfg, use_cuda):
+    return DeepSort(cfg.DEEPSORT.REID_CKPT, 
+                max_dist=cfg.DEEPSORT.MAX_DIST, min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE, 
+                nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE, 
+                max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET, use_cuda=use_cuda)
+    
+
+
+
+
+
+
+
+
+

yolov5/deep_sort_pytorch/deep_sort/deep/evaluate.py

@@ -0,0 +1,13 @@
+import torch
+
+features = torch.load("features.pth")
+qf = features["qf"]
+ql = features["ql"]
+gf = features["gf"]
+gl = features["gl"]
+
+scores = qf.mm(gf.t())
+res = scores.topk(5, dim=1)[1][:, 0]
+top1correct = gl[res].eq(ql).sum().item()
+
+print("Acc top1:{:.3f}".format(top1correct / ql.size(0)))

yolov5/deep_sort_pytorch/deep_sort/deep/feature_extractor.py

@@ -0,0 +1,54 @@
+import torch
+import torchvision.transforms as transforms
+import numpy as np
+import cv2
+import logging
+
+from .model import Net
+
+
+class Extractor(object):
+    def __init__(self, model_path, use_cuda=True):
+        self.net = Net(reid=True)
+        self.device = "cuda" if torch.cuda.is_available() and use_cuda else "cpu"
+        state_dict = torch.load(model_path, map_location=lambda storage, loc: storage)[
+            'net_dict']
+        self.net.load_state_dict(state_dict)
+        logger = logging.getLogger("root.tracker")
+        logger.info("Loading weights from {}... Done!".format(model_path))
+        self.net.to(self.device)
+        self.size = (64, 128)
+        self.norm = transforms.Compose([
+            transforms.ToTensor(),
+            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
+        ])
+
+    def _preprocess(self, im_crops):
+        """
+        TODO:
+            1. to float with scale from 0 to 1
+            2. resize to (64, 128) as Market1501 dataset did
+            3. concatenate to a numpy array
+            3. to torch Tensor
+            4. normalize
+        """
+        def _resize(im, size):
+            return cv2.resize(im.astype(np.float32)/255., size)
+
+        im_batch = torch.cat([self.norm(_resize(im, self.size)).unsqueeze(
+            0) for im in im_crops], dim=0).float()
+        return im_batch
+
+    def __call__(self, im_crops):
+        im_batch = self._preprocess(im_crops)
+        with torch.no_grad():
+            im_batch = im_batch.to(self.device)
+            features = self.net(im_batch)
+        return features.cpu().numpy()
+
+
+if __name__ == '__main__':
+    img = cv2.imread("demo.jpg")[:, :, (2, 1, 0)]
+    extr = Extractor("checkpoint/ckpt.t7")
+    feature = extr(img)
+    print(feature.shape)

yolov5/deep_sort_pytorch/deep_sort/deep/model.py

@@ -0,0 +1,109 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class BasicBlock(nn.Module):
+    def __init__(self, c_in, c_out, is_downsample=False):
+        super(BasicBlock, self).__init__()
+        self.is_downsample = is_downsample
+        if is_downsample:
+            self.conv1 = nn.Conv2d(
+                c_in, c_out, 3, stride=2, padding=1, bias=False)
+        else:
+            self.conv1 = nn.Conv2d(
+                c_in, c_out, 3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(c_out)
+        self.relu = nn.ReLU(True)
+        self.conv2 = nn.Conv2d(c_out, c_out, 3, stride=1,
+                               padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(c_out)
+        if is_downsample:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(c_in, c_out, 1, stride=2, bias=False),
+                nn.BatchNorm2d(c_out)
+            )
+        elif c_in != c_out:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(c_in, c_out, 1, stride=1, bias=False),
+                nn.BatchNorm2d(c_out)
+            )
+            self.is_downsample = True
+
+    def forward(self, x):
+        y = self.conv1(x)
+        y = self.bn1(y)
+        y = self.relu(y)
+        y = self.conv2(y)
+        y = self.bn2(y)
+        if self.is_downsample:
+            x = self.downsample(x)
+        return F.relu(x.add(y), True)
+
+
+def make_layers(c_in, c_out, repeat_times, is_downsample=False):
+    blocks = []
+    for i in range(repeat_times):
+        if i == 0:
+            blocks += [BasicBlock(c_in, c_out, is_downsample=is_downsample), ]
+        else:
+            blocks += [BasicBlock(c_out, c_out), ]
+    return nn.Sequential(*blocks)
+
+
+class Net(nn.Module):
+    def __init__(self, num_classes=751, reid=False):
+        super(Net, self).__init__()
+        # 3 128 64
+        self.conv = nn.Sequential(
+            nn.Conv2d(3, 64, 3, stride=1, padding=1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True),
+            # nn.Conv2d(32,32,3,stride=1,padding=1),
+            # nn.BatchNorm2d(32),
+            # nn.ReLU(inplace=True),
+            nn.MaxPool2d(3, 2, padding=1),
+        )
+        # 32 64 32
+        self.layer1 = make_layers(64, 64, 2, False)
+        # 32 64 32
+        self.layer2 = make_layers(64, 128, 2, True)
+        # 64 32 16
+        self.layer3 = make_layers(128, 256, 2, True)
+        # 128 16 8
+        self.layer4 = make_layers(256, 512, 2, True)
+        # 256 8 4
+        self.avgpool = nn.AvgPool2d((8, 4), 1)
+        # 256 1 1
+        self.reid = reid
+        self.classifier = nn.Sequential(
+            nn.Linear(512, 256),
+            nn.BatchNorm1d(256),
+            nn.ReLU(inplace=True),
+            nn.Dropout(),
+            nn.Linear(256, num_classes),
+        )
+
+    def forward(self, x):
+        x = self.conv(x)
+        x = self.layer1(x)
+        x = self.layer2(x)
+        x = self.layer3(x)
+        x = self.layer4(x)
+        x = self.avgpool(x)
+        x = x.view(x.size(0), -1)
+        # B x 128
+        if self.reid:
+            x = x.div(x.norm(p=2, dim=1, keepdim=True))
+            return x
+        # classifier
+        x = self.classifier(x)
+        return x
+
+
+if __name__ == '__main__':
+    net = Net()
+    x = torch.randn(4, 3, 128, 64)
+    y = net(x)
+    import ipdb
+    ipdb.set_trace()

yolov5/deep_sort_pytorch/deep_sort/deep/original_model.py

@@ -0,0 +1,111 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class BasicBlock(nn.Module):
+    def __init__(self, c_in, c_out, is_downsample=False):
+        super(BasicBlock, self).__init__()
+        self.is_downsample = is_downsample
+        if is_downsample:
+            self.conv1 = nn.Conv2d(
+                c_in, c_out, 3, stride=2, padding=1, bias=False)
+        else:
+            self.conv1 = nn.Conv2d(
+                c_in, c_out, 3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(c_out)
+        self.relu = nn.ReLU(True)
+        self.conv2 = nn.Conv2d(c_out, c_out, 3, stride=1,
+                               padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(c_out)
+        if is_downsample:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(c_in, c_out, 1, stride=2, bias=False),
+                nn.BatchNorm2d(c_out)
+            )
+        elif c_in != c_out:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(c_in, c_out, 1, stride=1, bias=False),
+                nn.BatchNorm2d(c_out)
+            )
+            self.is_downsample = True
+
+    def forward(self, x):
+        y = self.conv1(x)
+        y = self.bn1(y)
+        y = self.relu(y)
+        y = self.conv2(y)
+        y = self.bn2(y)
+        if self.is_downsample:
+            x = self.downsample(x)
+        return F.relu(x.add(y), True)
+
+
+def make_layers(c_in, c_out, repeat_times, is_downsample=False):
+    blocks = []
+    for i in range(repeat_times):
+        if i == 0:
+            blocks += [BasicBlock(c_in, c_out, is_downsample=is_downsample), ]
+        else:
+            blocks += [BasicBlock(c_out, c_out), ]
+    return nn.Sequential(*blocks)
+
+
+class Net(nn.Module):
+    def __init__(self, num_classes=625, reid=False):
+        super(Net, self).__init__()
+        # 3 128 64
+        self.conv = nn.Sequential(
+            nn.Conv2d(3, 32, 3, stride=1, padding=1),
+            nn.BatchNorm2d(32),
+            nn.ELU(inplace=True),
+            nn.Conv2d(32, 32, 3, stride=1, padding=1),
+            nn.BatchNorm2d(32),
+            nn.ELU(inplace=True),
+            nn.MaxPool2d(3, 2, padding=1),
+        )
+        # 32 64 32
+        self.layer1 = make_layers(32, 32, 2, False)
+        # 32 64 32
+        self.layer2 = make_layers(32, 64, 2, True)
+        # 64 32 16
+        self.layer3 = make_layers(64, 128, 2, True)
+        # 128 16 8
+        self.dense = nn.Sequential(
+            nn.Dropout(p=0.6),
+            nn.Linear(128*16*8, 128),
+            nn.BatchNorm1d(128),
+            nn.ELU(inplace=True)
+        )
+        # 256 1 1
+        self.reid = reid
+        self.batch_norm = nn.BatchNorm1d(128)
+        self.classifier = nn.Sequential(
+            nn.Linear(128, num_classes),
+        )
+
+    def forward(self, x):
+        x = self.conv(x)
+        x = self.layer1(x)
+        x = self.layer2(x)
+        x = self.layer3(x)
+
+        x = x.view(x.size(0), -1)
+        if self.reid:
+            x = self.dense[0](x)
+            x = self.dense[1](x)
+            x = x.div(x.norm(p=2, dim=1, keepdim=True))
+            return x
+        x = self.dense(x)
+        # B x 128
+        # classifier
+        x = self.classifier(x)
+        return x
+
+
+if __name__ == '__main__':
+    net = Net(reid=True)
+    x = torch.randn(4, 3, 128, 64)
+    y = net(x)
+    import ipdb
+    ipdb.set_trace()

yolov5/deep_sort_pytorch/deep_sort/deep/test.py

@@ -0,0 +1,80 @@
+import torch
+import torch.backends.cudnn as cudnn
+import torchvision
+
+import argparse
+import os
+
+from model import Net
+
+parser = argparse.ArgumentParser(description="Train on market1501")
+parser.add_argument("--data-dir", default='data', type=str)
+parser.add_argument("--no-cuda", action="store_true")
+parser.add_argument("--gpu-id", default=0, type=int)
+args = parser.parse_args()
+
+# device
+device = "cuda:{}".format(
+    args.gpu_id) if torch.cuda.is_available() and not args.no_cuda else "cpu"
+if torch.cuda.is_available() and not args.no_cuda:
+    cudnn.benchmark = True
+
+# data loader
+root = args.data_dir
+query_dir = os.path.join(root, "query")
+gallery_dir = os.path.join(root, "gallery")
+transform = torchvision.transforms.Compose([
+    torchvision.transforms.Resize((128, 64)),
+    torchvision.transforms.ToTensor(),
+    torchvision.transforms.Normalize(
+        [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+])
+queryloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(query_dir, transform=transform),
+    batch_size=64, shuffle=False
+)
+galleryloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(gallery_dir, transform=transform),
+    batch_size=64, shuffle=False
+)
+
+# net definition
+net = Net(reid=True)
+assert os.path.isfile(
+    "./checkpoint/ckpt.t7"), "Error: no checkpoint file found!"
+print('Loading from checkpoint/ckpt.t7')
+checkpoint = torch.load("./checkpoint/ckpt.t7")
+net_dict = checkpoint['net_dict']
+net.load_state_dict(net_dict, strict=False)
+net.eval()
+net.to(device)
+
+# compute features
+query_features = torch.tensor([]).float()
+query_labels = torch.tensor([]).long()
+gallery_features = torch.tensor([]).float()
+gallery_labels = torch.tensor([]).long()
+
+with torch.no_grad():
+    for idx, (inputs, labels) in enumerate(queryloader):
+        inputs = inputs.to(device)
+        features = net(inputs).cpu()
+        query_features = torch.cat((query_features, features), dim=0)
+        query_labels = torch.cat((query_labels, labels))
+
+    for idx, (inputs, labels) in enumerate(galleryloader):
+        inputs = inputs.to(device)
+        features = net(inputs).cpu()
+        gallery_features = torch.cat((gallery_features, features), dim=0)
+        gallery_labels = torch.cat((gallery_labels, labels))
+
+gallery_labels -= 2
+
+# save features
+features = {
+    "qf": query_features,
+    "ql": query_labels,
+    "gf": gallery_features,
+    "gl": gallery_labels
+}
+torch.save(features, "features.pth")

yolov5/deep_sort_pytorch/deep_sort/deep/train.py

@@ -0,0 +1,206 @@
+import argparse
+import os
+import time
+
+import numpy as np
+import matplotlib.pyplot as plt
+import torch
+import torch.backends.cudnn as cudnn
+import torchvision
+
+from model import Net
+
+parser = argparse.ArgumentParser(description="Train on market1501")
+parser.add_argument("--data-dir", default='data', type=str)
+parser.add_argument("--no-cuda", action="store_true")
+parser.add_argument("--gpu-id", default=0, type=int)
+parser.add_argument("--lr", default=0.1, type=float)
+parser.add_argument("--interval", '-i', default=20, type=int)
+parser.add_argument('--resume', '-r', action='store_true')
+args = parser.parse_args()
+
+# device
+device = "cuda:{}".format(
+    args.gpu_id) if torch.cuda.is_available() and not args.no_cuda else "cpu"
+if torch.cuda.is_available() and not args.no_cuda:
+    cudnn.benchmark = True
+
+# data loading
+root = args.data_dir
+train_dir = os.path.join(root, "train")
+test_dir = os.path.join(root, "test")
+transform_train = torchvision.transforms.Compose([
+    torchvision.transforms.RandomCrop((128, 64), padding=4),
+    torchvision.transforms.RandomHorizontalFlip(),
+    torchvision.transforms.ToTensor(),
+    torchvision.transforms.Normalize(
+        [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+])
+transform_test = torchvision.transforms.Compose([
+    torchvision.transforms.Resize((128, 64)),
+    torchvision.transforms.ToTensor(),
+    torchvision.transforms.Normalize(
+        [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+])
+trainloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(train_dir, transform=transform_train),
+    batch_size=64, shuffle=True
+)
+testloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(test_dir, transform=transform_test),
+    batch_size=64, shuffle=True
+)
+num_classes = max(len(trainloader.dataset.classes),
+                  len(testloader.dataset.classes))
+
+# net definition
+start_epoch = 0
+net = Net(num_classes=num_classes)
+if args.resume:
+    assert os.path.isfile(
+        "./checkpoint/ckpt.t7"), "Error: no checkpoint file found!"
+    print('Loading from checkpoint/ckpt.t7')
+    checkpoint = torch.load("./checkpoint/ckpt.t7")
+    # import ipdb; ipdb.set_trace()
+    net_dict = checkpoint['net_dict']
+    net.load_state_dict(net_dict)
+    best_acc = checkpoint['acc']
+    start_epoch = checkpoint['epoch']
+net.to(device)
+
+# loss and optimizer
+criterion = torch.nn.CrossEntropyLoss()
+optimizer = torch.optim.SGD(
+    net.parameters(), args.lr, momentum=0.9, weight_decay=5e-4)
+best_acc = 0.
+
+# train function for each epoch
+
+
+def train(epoch):
+    print("\nEpoch : %d" % (epoch+1))
+    net.train()
+    training_loss = 0.
+    train_loss = 0.
+    correct = 0
+    total = 0
+    interval = args.interval
+    start = time.time()
+    for idx, (inputs, labels) in enumerate(trainloader):
+        # forward
+        inputs, labels = inputs.to(device), labels.to(device)
+        outputs = net(inputs)
+        loss = criterion(outputs, labels)
+
+        # backward
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+        # accumurating
+        training_loss += loss.item()
+        train_loss += loss.item()
+        correct += outputs.max(dim=1)[1].eq(labels).sum().item()
+        total += labels.size(0)
+
+        # print
+        if (idx+1) % interval == 0:
+            end = time.time()
+            print("[progress:{:.1f}%]time:{:.2f}s Loss:{:.5f} Correct:{}/{} Acc:{:.3f}%".format(
+                100.*(idx+1)/len(trainloader), end-start, training_loss /
+                interval, correct, total, 100.*correct/total
+            ))
+            training_loss = 0.
+            start = time.time()
+
+    return train_loss/len(trainloader), 1. - correct/total
+
+
+def test(epoch):
+    global best_acc
+    net.eval()
+    test_loss = 0.
+    correct = 0
+    total = 0
+    start = time.time()
+    with torch.no_grad():
+        for idx, (inputs, labels) in enumerate(testloader):
+            inputs, labels = inputs.to(device), labels.to(device)
+            outputs = net(inputs)
+            loss = criterion(outputs, labels)
+
+            test_loss += loss.item()
+            correct += outputs.max(dim=1)[1].eq(labels).sum().item()
+            total += labels.size(0)
+
+        print("Testing ...")
+        end = time.time()
+        print("[progress:{:.1f}%]time:{:.2f}s Loss:{:.5f} Correct:{}/{} Acc:{:.3f}%".format(
+            100.*(idx+1)/len(testloader), end-start, test_loss /
+            len(testloader), correct, total, 100.*correct/total
+        ))
+
+    # saving checkpoint
+    acc = 100.*correct/total
+    if acc > best_acc:
+        best_acc = acc
+        print("Saving parameters to checkpoint/ckpt.t7")
+        checkpoint = {
+            'net_dict': net.state_dict(),
+            'acc': acc,
+            'epoch': epoch,
+        }
+        if not os.path.isdir('checkpoint'):
+            os.mkdir('checkpoint')
+        torch.save(checkpoint, './checkpoint/ckpt.t7')
+
+    return test_loss/len(testloader), 1. - correct/total
+
+
+# plot figure
+x_epoch = []
+record = {'train_loss': [], 'train_err': [], 'test_loss': [], 'test_err': []}
+fig = plt.figure()
+ax0 = fig.add_subplot(121, title="loss")
+ax1 = fig.add_subplot(122, title="top1err")
+
+
+def draw_curve(epoch, train_loss, train_err, test_loss, test_err):
+    global record
+    record['train_loss'].append(train_loss)
+    record['train_err'].append(train_err)
+    record['test_loss'].append(test_loss)
+    record['test_err'].append(test_err)
+
+    x_epoch.append(epoch)
+    ax0.plot(x_epoch, record['train_loss'], 'bo-', label='train')
+    ax0.plot(x_epoch, record['test_loss'], 'ro-', label='val')
+    ax1.plot(x_epoch, record['train_err'], 'bo-', label='train')
+    ax1.plot(x_epoch, record['test_err'], 'ro-', label='val')
+    if epoch == 0:
+        ax0.legend()
+        ax1.legend()
+    fig.savefig("train.jpg")
+
+# lr decay
+
+
+def lr_decay():
+    global optimizer
+    for params in optimizer.param_groups:
+        params['lr'] *= 0.1
+        lr = params['lr']
+        print("Learning rate adjusted to {}".format(lr))
+
+
+def main():
+    for epoch in range(start_epoch, start_epoch+40):
+        train_loss, train_err = train(epoch)
+        test_loss, test_err = test(epoch)
+        draw_curve(epoch, train_loss, train_err, test_loss, test_err)
+        if (epoch+1) % 20 == 0:
+            lr_decay()
+
+
+if __name__ == '__main__':
+    main()

yolov5/deep_sort_pytorch/deep_sort/deep_sort.py

@@ -0,0 +1,117 @@
+import numpy as np
+import torch
+
+from .deep.feature_extractor import Extractor
+from .sort.nn_matching import NearestNeighborDistanceMetric
+from .sort.preprocessing import non_max_suppression
+from .sort.detection import Detection
+from .sort.tracker import Tracker
+
+
+__all__ = ['DeepSort']
+
+
+class DeepSort(object):
+    def __init__(self, model_path, max_dist=0.2, min_confidence=0.3, nms_max_overlap=1.0, max_iou_distance=0.7, max_age=70, n_init=3, nn_budget=100, use_cuda=True):
+        self.min_confidence = min_confidence
+        self.nms_max_overlap = nms_max_overlap
+
+        self.extractor = Extractor(model_path, use_cuda=use_cuda)
+
+        max_cosine_distance = max_dist
+        nn_budget = 100
+        metric = NearestNeighborDistanceMetric(
+            "cosine", max_cosine_distance, nn_budget)
+        self.tracker = Tracker(
+            metric, max_iou_distance=max_iou_distance, max_age=max_age, n_init=n_init)
+
+    def update(self, bbox_xywh, confidences, ori_img):
+        self.height, self.width = ori_img.shape[:2]
+        # generate detections
+        features = self._get_features(bbox_xywh, ori_img)
+        bbox_tlwh = self._xywh_to_tlwh(bbox_xywh)
+        detections = [Detection(bbox_tlwh[i], conf, features[i]) for i, conf in enumerate(
+            confidences) if conf > self.min_confidence]
+
+        # run on non-maximum supression
+        boxes = np.array([d.tlwh for d in detections])
+        scores = np.array([d.confidence for d in detections])
+        indices = non_max_suppression(boxes, self.nms_max_overlap, scores)
+        detections = [detections[i] for i in indices]
+
+        # update tracker
+        self.tracker.predict()
+        self.tracker.update(detections)
+
+        # output bbox identities
+        outputs = []
+        for track in self.tracker.tracks:
+            if not track.is_confirmed() or track.time_since_update > 1:
+                continue
+            box = track.to_tlwh()
+            x1, y1, x2, y2 = self._tlwh_to_xyxy(box)
+            track_id = track.track_id
+            outputs.append(np.array([x1, y1, x2, y2, track_id], dtype=np.int))
+        if len(outputs) > 0:
+            outputs = np.stack(outputs, axis=0)
+        return outputs
+
+    """
+    TODO:
+        Convert bbox from xc_yc_w_h to xtl_ytl_w_h
+    Thanks JieChen91@github.com for reporting this bug!
+    """
+    @staticmethod
+    def _xywh_to_tlwh(bbox_xywh):
+        if isinstance(bbox_xywh, np.ndarray):
+            bbox_tlwh = bbox_xywh.copy()
+        elif isinstance(bbox_xywh, torch.Tensor):
+            bbox_tlwh = bbox_xywh.clone()
+        bbox_tlwh[:, 0] = bbox_xywh[:, 0] - bbox_xywh[:, 2] / 2.
+        bbox_tlwh[:, 1] = bbox_xywh[:, 1] - bbox_xywh[:, 3] / 2.
+        return bbox_tlwh
+
+    def _xywh_to_xyxy(self, bbox_xywh):
+        x, y, w, h = bbox_xywh
+        x1 = max(int(x - w / 2), 0)
+        x2 = min(int(x + w / 2), self.width - 1)
+        y1 = max(int(y - h / 2), 0)
+        y2 = min(int(y + h / 2), self.height - 1)
+        return x1, y1, x2, y2
+
+    def _tlwh_to_xyxy(self, bbox_tlwh):
+        """
+        TODO:
+            Convert bbox from xtl_ytl_w_h to xc_yc_w_h
+        Thanks JieChen91@github.com for reporting this bug!
+        """
+        x, y, w, h = bbox_tlwh
+        x1 = max(int(x), 0)
+        x2 = min(int(x+w), self.width - 1)
+        y1 = max(int(y), 0)
+        y2 = min(int(y+h), self.height - 1)
+        return x1, y1, x2, y2
+
+    def increment_ages(self):
+        self.tracker.increment_ages()
+
+    def _xyxy_to_tlwh(self, bbox_xyxy):
+        x1, y1, x2, y2 = bbox_xyxy
+
+        t = x1
+        l = y1
+        w = int(x2 - x1)
+        h = int(y2 - y1)
+        return t, l, w, h
+
+    def _get_features(self, bbox_xywh, ori_img):
+        im_crops = []
+        for box in bbox_xywh:
+            x1, y1, x2, y2 = self._xywh_to_xyxy(box)
+            im = ori_img[y1:y2, x1:x2]
+            im_crops.append(im)
+        if im_crops:
+            features = self.extractor(im_crops)
+        else:
+            features = np.array([])
+        return features

yolov5/deep_sort_pytorch/deep_sort/sort/detection.py

@@ -0,0 +1,49 @@
+# vim: expandtab:ts=4:sw=4
+import numpy as np
+
+
+class Detection(object):
+    """
+    This class represents a bounding box detection in a single image.
+
+    Parameters
+    ----------
+    tlwh : array_like
+        Bounding box in format `(x, y, w, h)`.
+    confidence : float
+        Detector confidence score.
+    feature : array_like
+        A feature vector that describes the object contained in this image.
+
+    Attributes
+    ----------
+    tlwh : ndarray
+        Bounding box in format `(top left x, top left y, width, height)`.
+    confidence : ndarray
+        Detector confidence score.
+    feature : ndarray | NoneType
+        A feature vector that describes the object contained in this image.
+
+    """
+
+    def __init__(self, tlwh, confidence, feature):
+        self.tlwh = np.asarray(tlwh, dtype=np.float)
+        self.confidence = float(confidence)
+        self.feature = np.asarray(feature, dtype=np.float32)
+
+    def to_tlbr(self):
+        """Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
+        `(top left, bottom right)`.
+        """
+        ret = self.tlwh.copy()
+        ret[2:] += ret[:2]
+        return ret
+
+    def to_xyah(self):
+        """Convert bounding box to format `(center x, center y, aspect ratio,
+        height)`, where the aspect ratio is `width / height`.
+        """
+        ret = self.tlwh.copy()
+        ret[:2] += ret[2:] / 2
+        ret[2] /= ret[3]
+        return ret

yolov5/deep_sort_pytorch/deep_sort/sort/iou_matching.py

@@ -0,0 +1,82 @@
+# vim: expandtab:ts=4:sw=4
+from __future__ import absolute_import
+import numpy as np
+from . import linear_assignment
+
+
+def iou(bbox, candidates):
+    """Computer intersection over union.
+
+    Parameters
+    ----------
+    bbox : ndarray
+        A bounding box in format `(top left x, top left y, width, height)`.
+    candidates : ndarray
+        A matrix of candidate bounding boxes (one per row) in the same format
+        as `bbox`.
+
+    Returns
+    -------
+    ndarray
+        The intersection over union in [0, 1] between the `bbox` and each
+        candidate. A higher score means a larger fraction of the `bbox` is
+        occluded by the candidate.
+
+    """
+    bbox_tl, bbox_br = bbox[:2], bbox[:2] + bbox[2:]
+    candidates_tl = candidates[:, :2]
+    candidates_br = candidates[:, :2] + candidates[:, 2:]
+
+    tl = np.c_[np.maximum(bbox_tl[0], candidates_tl[:, 0])[:, np.newaxis],
+               np.maximum(bbox_tl[1], candidates_tl[:, 1])[:, np.newaxis]]
+    br = np.c_[np.minimum(bbox_br[0], candidates_br[:, 0])[:, np.newaxis],
+               np.minimum(bbox_br[1], candidates_br[:, 1])[:, np.newaxis]]
+    wh = np.maximum(0., br - tl)
+
+    area_intersection = wh.prod(axis=1)
+    area_bbox = bbox[2:].prod()
+    area_candidates = candidates[:, 2:].prod(axis=1)
+    return area_intersection / (area_bbox + area_candidates - area_intersection)
+
+
+def iou_cost(tracks, detections, track_indices=None,
+             detection_indices=None):
+    """An intersection over union distance metric.
+
+    Parameters
+    ----------
+    tracks : List[deep_sort.track.Track]
+        A list of tracks.
+    detections : List[deep_sort.detection.Detection]
+        A list of detections.
+    track_indices : Optional[List[int]]
+        A list of indices to tracks that should be matched. Defaults to
+        all `tracks`.
+    detection_indices : Optional[List[int]]
+        A list of indices to detections that should be matched. Defaults
+        to all `detections`.
+
+    Returns
+    -------
+    ndarray
+        Returns a cost matrix of shape
+        len(track_indices), len(detection_indices) where entry (i, j) is
+        `1 - iou(tracks[track_indices[i]], detections[detection_indices[j]])`.
+
+    """
+    if track_indices is None:
+        track_indices = np.arange(len(tracks))
+    if detection_indices is None:
+        detection_indices = np.arange(len(detections))
+
+    cost_matrix = np.zeros((len(track_indices), len(detection_indices)))
+    for row, track_idx in enumerate(track_indices):
+        if tracks[track_idx].time_since_update > 1:
+            cost_matrix[row, :] = linear_assignment.INFTY_COST
+            continue
+
+        bbox = tracks[track_idx].to_tlwh()
+        candidates = np.asarray(
+            [detections[i].tlwh for i in detection_indices])
+        cost_matrix[row, :] = 1. - iou(bbox, candidates)
+    return cost_matrix

yolov5/deep_sort_pytorch/deep_sort/sort/kalman_filter.py

@@ -0,0 +1,229 @@
+# vim: expandtab:ts=4:sw=4
+import numpy as np
+import scipy.linalg
+
+
+"""
+Table for the 0.95 quantile of the chi-square distribution with N degrees of
+freedom (contains values for N=1, ..., 9). Taken from MATLAB/Octave's chi2inv
+function and used as Mahalanobis gating threshold.
+"""
+chi2inv95 = {
+    1: 3.8415,
+    2: 5.9915,
+    3: 7.8147,
+    4: 9.4877,
+    5: 11.070,
+    6: 12.592,
+    7: 14.067,
+    8: 15.507,
+    9: 16.919}
+
+
+class KalmanFilter(object):
+    """
+    A simple Kalman filter for tracking bounding boxes in image space.
+
+    The 8-dimensional state space
+
+        x, y, a, h, vx, vy, va, vh
+
+    contains the bounding box center position (x, y), aspect ratio a, height h,
+    and their respective velocities.
+
+    Object motion follows a constant velocity model. The bounding box location
+    (x, y, a, h) is taken as direct observation of the state space (linear
+    observation model).
+
+    """
+
+    def __init__(self):
+        ndim, dt = 4, 1.
+
+        # Create Kalman filter model matrices.
+        self._motion_mat = np.eye(2 * ndim, 2 * ndim)
+        for i in range(ndim):
+            self._motion_mat[i, ndim + i] = dt
+        self._update_mat = np.eye(ndim, 2 * ndim)
+
+        # Motion and observation uncertainty are chosen relative to the current
+        # state estimate. These weights control the amount of uncertainty in
+        # the model. This is a bit hacky.
+        self._std_weight_position = 1. / 20
+        self._std_weight_velocity = 1. / 160
+
+    def initiate(self, measurement):
+        """Create track from unassociated measurement.
+
+        Parameters
+        ----------
+        measurement : ndarray
+            Bounding box coordinates (x, y, a, h) with center position (x, y),
+            aspect ratio a, and height h.
+
+        Returns
+        -------
+        (ndarray, ndarray)
+            Returns the mean vector (8 dimensional) and covariance matrix (8x8
+            dimensional) of the new track. Unobserved velocities are initialized
+            to 0 mean.
+
+        """
+        mean_pos = measurement
+        mean_vel = np.zeros_like(mean_pos)
+        mean = np.r_[mean_pos, mean_vel]
+
+        std = [
+            2 * self._std_weight_position * measurement[3],
+            2 * self._std_weight_position * measurement[3],
+            1e-2,
+            2 * self._std_weight_position * measurement[3],
+            10 * self._std_weight_velocity * measurement[3],
+            10 * self._std_weight_velocity * measurement[3],
+            1e-5,
+            10 * self._std_weight_velocity * measurement[3]]
+        covariance = np.diag(np.square(std))
+        return mean, covariance
+
+    def predict(self, mean, covariance):
+        """Run Kalman filter prediction step.
+
+        Parameters
+        ----------
+        mean : ndarray
+            The 8 dimensional mean vector of the object state at the previous
+            time step.
+        covariance : ndarray
+            The 8x8 dimensional covariance matrix of the object state at the
+            previous time step.
+
+        Returns
+        -------
+        (ndarray, ndarray)
+            Returns the mean vector and covariance matrix of the predicted
+            state. Unobserved velocities are initialized to 0 mean.
+
+        """
+        std_pos = [
+            self._std_weight_position * mean[3],
+            self._std_weight_position * mean[3],
+            1e-2,
+            self._std_weight_position * mean[3]]
+        std_vel = [
+            self._std_weight_velocity * mean[3],
+            self._std_weight_velocity * mean[3],
+            1e-5,
+            self._std_weight_velocity * mean[3]]
+        motion_cov = np.diag(np.square(np.r_[std_pos, std_vel]))
+
+        mean = np.dot(self._motion_mat, mean)
+        covariance = np.linalg.multi_dot((
+            self._motion_mat, covariance, self._motion_mat.T)) + motion_cov
+
+        return mean, covariance
+
+    def project(self, mean, covariance):
+        """Project state distribution to measurement space.
+
+        Parameters
+        ----------
+        mean : ndarray
+            The state's mean vector (8 dimensional array).
+        covariance : ndarray
+            The state's covariance matrix (8x8 dimensional).
+
+        Returns
+        -------
+        (ndarray, ndarray)
+            Returns the projected mean and covariance matrix of the given state
+            estimate.
+
+        """
+        std = [
+            self._std_weight_position * mean[3],
+            self._std_weight_position * mean[3],
+            1e-1,
+            self._std_weight_position * mean[3]]
+        innovation_cov = np.diag(np.square(std))
+
+        mean = np.dot(self._update_mat, mean)
+        covariance = np.linalg.multi_dot((
+            self._update_mat, covariance, self._update_mat.T))
+        return mean, covariance + innovation_cov
+
+    def update(self, mean, covariance, measurement):
+        """Run Kalman filter correction step.
+
+        Parameters
+        ----------
+        mean : ndarray
+            The predicted state's mean vector (8 dimensional).
+        covariance : ndarray
+            The state's covariance matrix (8x8 dimensional).
+        measurement : ndarray
+            The 4 dimensional measurement vector (x, y, a, h), where (x, y)
+            is the center position, a the aspect ratio, and h the height of the
+            bounding box.
+
+        Returns
+        -------
+        (ndarray, ndarray)
+            Returns the measurement-corrected state distribution.
+
+        """
+        projected_mean, projected_cov = self.project(mean, covariance)
+
+        chol_factor, lower = scipy.linalg.cho_factor(
+            projected_cov, lower=True, check_finite=False)
+        kalman_gain = scipy.linalg.cho_solve(
+            (chol_factor, lower), np.dot(covariance, self._update_mat.T).T,
+            check_finite=False).T
+        innovation = measurement - projected_mean
+
+        new_mean = mean + np.dot(innovation, kalman_gain.T)
+        new_covariance = covariance - np.linalg.multi_dot((
+            kalman_gain, projected_cov, kalman_gain.T))
+        return new_mean, new_covariance
+
+    def gating_distance(self, mean, covariance, measurements,
+                        only_position=False):
+        """Compute gating distance between state distribution and measurements.
+
+        A suitable distance threshold can be obtained from `chi2inv95`. If
+        `only_position` is False, the chi-square distribution has 4 degrees of
+        freedom, otherwise 2.
+
+        Parameters
+        ----------
+        mean : ndarray
+            Mean vector over the state distribution (8 dimensional).
+        covariance : ndarray
+            Covariance of the state distribution (8x8 dimensional).
+        measurements : ndarray
+            An Nx4 dimensional matrix of N measurements, each in
+            format (x, y, a, h) where (x, y) is the bounding box center
+            position, a the aspect ratio, and h the height.
+        only_position : Optional[bool]
+            If True, distance computation is done with respect to the bounding
+            box center position only.
+
+        Returns
+        -------
+        ndarray
+            Returns an array of length N, where the i-th element contains the
+            squared Mahalanobis distance between (mean, covariance) and
+            `measurements[i]`.
+
+        """
+        mean, covariance = self.project(mean, covariance)
+        if only_position:
+            mean, covariance = mean[:2], covariance[:2, :2]
+            measurements = measurements[:, :2]
+
+        cholesky_factor = np.linalg.cholesky(covariance)
+        d = measurements - mean
+        z = scipy.linalg.solve_triangular(
+            cholesky_factor, d.T, lower=True, check_finite=False,
+            overwrite_b=True)
+        squared_maha = np.sum(z * z, axis=0)
+        return squared_maha

yolov5/deep_sort_pytorch/deep_sort/sort/linear_assignment.py

@@ -0,0 +1,192 @@
+# vim: expandtab:ts=4:sw=4
+from __future__ import absolute_import
+import numpy as np
+# from sklearn.utils.linear_assignment_ import linear_assignment
+from scipy.optimize import linear_sum_assignment as linear_assignment
+from . import kalman_filter
+
+
+INFTY_COST = 1e+5
+
+
+def min_cost_matching(
+        distance_metric, max_distance, tracks, detections, track_indices=None,
+        detection_indices=None):
+    """Solve linear assignment problem.
+
+    Parameters
+    ----------
+    distance_metric : Callable[List[Track], List[Detection], List[int], List[int]) -> ndarray
+        The distance metric is given a list of tracks and detections as well as
+        a list of N track indices and M detection indices. The metric should
+        return the NxM dimensional cost matrix, where element (i, j) is the
+        association cost between the i-th track in the given track indices and
+        the j-th detection in the given detection_indices.
+    max_distance : float
+        Gating threshold. Associations with cost larger than this value are
+        disregarded.
+    tracks : List[track.Track]
+        A list of predicted tracks at the current time step.
+    detections : List[detection.Detection]
+        A list of detections at the current time step.
+    track_indices : List[int]
+        List of track indices that maps rows in `cost_matrix` to tracks in
+        `tracks` (see description above).
+    detection_indices : List[int]
+        List of detection indices that maps columns in `cost_matrix` to
+        detections in `detections` (see description above).
+
+    Returns
+    -------
+    (List[(int, int)], List[int], List[int])
+        Returns a tuple with the following three entries:
+        * A list of matched track and detection indices.
+        * A list of unmatched track indices.
+        * A list of unmatched detection indices.
+
+    """
+    if track_indices is None:
+        track_indices = np.arange(len(tracks))
+    if detection_indices is None:
+        detection_indices = np.arange(len(detections))
+
+    if len(detection_indices) == 0 or len(track_indices) == 0:
+        return [], track_indices, detection_indices  # Nothing to match.
+
+    cost_matrix = distance_metric(
+        tracks, detections, track_indices, detection_indices)
+    cost_matrix[cost_matrix > max_distance] = max_distance + 1e-5
+
+    row_indices, col_indices = linear_assignment(cost_matrix)
+
+    matches, unmatched_tracks, unmatched_detections = [], [], []
+    for col, detection_idx in enumerate(detection_indices):
+        if col not in col_indices:
+            unmatched_detections.append(detection_idx)
+    for row, track_idx in enumerate(track_indices):
+        if row not in row_indices:
+            unmatched_tracks.append(track_idx)
+    for row, col in zip(row_indices, col_indices):
+        track_idx = track_indices[row]
+        detection_idx = detection_indices[col]
+        if cost_matrix[row, col] > max_distance:
+            unmatched_tracks.append(track_idx)
+            unmatched_detections.append(detection_idx)
+        else:
+            matches.append((track_idx, detection_idx))
+    return matches, unmatched_tracks, unmatched_detections
+
+
+def matching_cascade(
+        distance_metric, max_distance, cascade_depth, tracks, detections,
+        track_indices=None, detection_indices=None):
+    """Run matching cascade.
+
+    Parameters
+    ----------
+    distance_metric : Callable[List[Track], List[Detection], List[int], List[int]) -> ndarray
+        The distance metric is given a list of tracks and detections as well as
+        a list of N track indices and M detection indices. The metric should
+        return the NxM dimensional cost matrix, where element (i, j) is the
+        association cost between the i-th track in the given track indices and
+        the j-th detection in the given detection indices.
+    max_distance : float
+        Gating threshold. Associations with cost larger than this value are
+        disregarded.
+    cascade_depth: int
+        The cascade depth, should be se to the maximum track age.
+    tracks : List[track.Track]
+        A list of predicted tracks at the current time step.
+    detections : List[detection.Detection]
+        A list of detections at the current time step.
+    track_indices : Optional[List[int]]
+        List of track indices that maps rows in `cost_matrix` to tracks in
+        `tracks` (see description above). Defaults to all tracks.
+    detection_indices : Optional[List[int]]
+        List of detection indices that maps columns in `cost_matrix` to
+        detections in `detections` (see description above). Defaults to all
+        detections.
+
+    Returns
+    -------
+    (List[(int, int)], List[int], List[int])
+        Returns a tuple with the following three entries:
+        * A list of matched track and detection indices.
+        * A list of unmatched track indices.
+        * A list of unmatched detection indices.
+
+    """
+    if track_indices is None:
+        track_indices = list(range(len(tracks)))
+    if detection_indices is None:
+        detection_indices = list(range(len(detections)))
+
+    unmatched_detections = detection_indices
+    matches = []
+    for level in range(cascade_depth):
+        if len(unmatched_detections) == 0:  # No detections left
+            break
+
+        track_indices_l = [
+            k for k in track_indices
+            if tracks[k].time_since_update == 1 + level
+        ]
+        if len(track_indices_l) == 0:  # Nothing to match at this level
+            continue
+
+        matches_l, _, unmatched_detections = \
+            min_cost_matching(
+                distance_metric, max_distance, tracks, detections,
+                track_indices_l, unmatched_detections)
+        matches += matches_l
+    unmatched_tracks = list(set(track_indices) - set(k for k, _ in matches))
+    return matches, unmatched_tracks, unmatched_detections
+
+
+def gate_cost_matrix(
+        kf, cost_matrix, tracks, detections, track_indices, detection_indices,
+        gated_cost=INFTY_COST, only_position=False):
+    """Invalidate infeasible entries in cost matrix based on the state
+    distributions obtained by Kalman filtering.
+
+    Parameters
+    ----------
+    kf : The Kalman filter.
+    cost_matrix : ndarray
+        The NxM dimensional cost matrix, where N is the number of track indices
+        and M is the number of detection indices, such that entry (i, j) is the
+        association cost between `tracks[track_indices[i]]` and
+        `detections[detection_indices[j]]`.
+    tracks : List[track.Track]
+        A list of predicted tracks at the current time step.
+    detections : List[detection.Detection]
+        A list of detections at the current time step.
+    track_indices : List[int]
+        List of track indices that maps rows in `cost_matrix` to tracks in
+        `tracks` (see description above).
+    detection_indices : List[int]
+        List of detection indices that maps columns in `cost_matrix` to
+        detections in `detections` (see description above).
+    gated_cost : Optional[float]
+        Entries in the cost matrix corresponding to infeasible associations are
+        set this value. Defaults to a very large value.
+    only_position : Optional[bool]
+        If True, only the x, y position of the state distribution is considered
+        during gating. Defaults to False.
+
+    Returns
+    -------
+    ndarray
+        Returns the modified cost matrix.
+
+    """
+    gating_dim = 2 if only_position else 4
+    gating_threshold = kalman_filter.chi2inv95[gating_dim]
+    measurements = np.asarray(
+        [detections[i].to_xyah() for i in detection_indices])
+    for row, track_idx in enumerate(track_indices):
+        track = tracks[track_idx]
+        gating_distance = kf.gating_distance(
+            track.mean, track.covariance, measurements, only_position)
+        cost_matrix[row, gating_distance > gating_threshold] = gated_cost
+    return cost_matrix

yolov5/deep_sort_pytorch/deep_sort/sort/nn_matching.py

@@ -0,0 +1,176 @@
+# vim: expandtab:ts=4:sw=4
+import numpy as np
+
+
+def _pdist(a, b):
+    """Compute pair-wise squared distance between points in `a` and `b`.
+
+    Parameters
+    ----------
+    a : array_like
+        An NxM matrix of N samples of dimensionality M.
+    b : array_like
+        An LxM matrix of L samples of dimensionality M.
+
+    Returns
+    -------
+    ndarray
+        Returns a matrix of size len(a), len(b) such that eleement (i, j)
+        contains the squared distance between `a[i]` and `b[j]`.
+
+    """
+    a, b = np.asarray(a), np.asarray(b)
+    if len(a) == 0 or len(b) == 0:
+        return np.zeros((len(a), len(b)))
+    a2, b2 = np.square(a).sum(axis=1), np.square(b).sum(axis=1)
+    r2 = -2. * np.dot(a, b.T) + a2[:, None] + b2[None, :]
+    r2 = np.clip(r2, 0., float(np.inf))
+    return r2
+
+
+def _cosine_distance(a, b, data_is_normalized=False):
+    """Compute pair-wise cosine distance between points in `a` and `b`.
+
+    Parameters
+    ----------
+    a : array_like
+        An NxM matrix of N samples of dimensionality M.
+    b : array_like
+        An LxM matrix of L samples of dimensionality M.
+    data_is_normalized : Optional[bool]
+        If True, assumes rows in a and b are unit length vectors.
+        Otherwise, a and b are explicitly normalized to lenght 1.
+
+    Returns
+    -------
+    ndarray
+        Returns a matrix of size len(a), len(b) such that eleement (i, j)
+        contains the squared distance between `a[i]` and `b[j]`.
+
+    """
+    if not data_is_normalized:
+        a = np.asarray(a) / np.linalg.norm(a, axis=1, keepdims=True)
+        b = np.asarray(b) / np.linalg.norm(b, axis=1, keepdims=True)
+    return 1. - np.dot(a, b.T)
+
+
+def _nn_euclidean_distance(x, y):
+    """ Helper function for nearest neighbor distance metric (Euclidean).
+
+    Parameters
+    ----------
+    x : ndarray
+        A matrix of N row-vectors (sample points).
+    y : ndarray
+        A matrix of M row-vectors (query points).
+
+    Returns
+    -------
+    ndarray
+        A vector of length M that contains for each entry in `y` the
+        smallest Euclidean distance to a sample in `x`.
+
+    """
+    distances = _pdist(x, y)
+    return np.maximum(0.0, distances.min(axis=0))
+
+
+def _nn_cosine_distance(x, y):
+    """ Helper function for nearest neighbor distance metric (cosine).
+
+    Parameters
+    ----------
+    x : ndarray
+        A matrix of N row-vectors (sample points).
+    y : ndarray
+        A matrix of M row-vectors (query points).
+
+    Returns
+    -------
+    ndarray
+        A vector of length M that contains for each entry in `y` the
+        smallest cosine distance to a sample in `x`.
+
+    """
+    distances = _cosine_distance(x, y)
+    return distances.min(axis=0)
+
+
+class NearestNeighborDistanceMetric(object):
+    """
+    A nearest neighbor distance metric that, for each target, returns
+    the closest distance to any sample that has been observed so far.
+
+    Parameters
+    ----------
+    metric : str
+        Either "euclidean" or "cosine".
+    matching_threshold: float
+        The matching threshold. Samples with larger distance are considered an
+        invalid match.
+    budget : Optional[int]
+        If not None, fix samples per class to at most this number. Removes
+        the oldest samples when the budget is reached.
+
+    Attributes
+    ----------
+    samples : Dict[int -> List[ndarray]]
+        A dictionary that maps from target identities to the list of samples
+        that have been observed so far.
+
+    """
+
+    def __init__(self, metric, matching_threshold, budget=None):
+
+        if metric == "euclidean":
+            self._metric = _nn_euclidean_distance
+        elif metric == "cosine":
+            self._metric = _nn_cosine_distance
+        else:
+            raise ValueError(
+                "Invalid metric; must be either 'euclidean' or 'cosine'")
+        self.matching_threshold = matching_threshold
+        self.budget = budget
+        self.samples = {}
+
+    def partial_fit(self, features, targets, active_targets):
+        """Update the distance metric with new data.
+
+        Parameters
+        ----------
+        features : ndarray
+            An NxM matrix of N features of dimensionality M.
+        targets : ndarray
+            An integer array of associated target identities.
+        active_targets : List[int]
+            A list of targets that are currently present in the scene.
+
+        """
+        for feature, target in zip(features, targets):
+            self.samples.setdefault(target, []).append(feature)
+            if self.budget is not None:
+                self.samples[target] = self.samples[target][-self.budget:]
+        self.samples = {k: self.samples[k] for k in active_targets}
+
+    def distance(self, features, targets):
+        """Compute distance between features and targets.
+
+        Parameters
+        ----------
+        features : ndarray
+            An NxM matrix of N features of dimensionality M.
+        targets : List[int]
+            A list of targets to match the given `features` against.
+
+        Returns
+        -------
+        ndarray
+            Returns a cost matrix of shape len(targets), len(features), where
+            element (i, j) contains the closest squared distance between
+            `targets[i]` and `features[j]`.
+
+        """
+        cost_matrix = np.zeros((len(targets), len(features)))
+        for i, target in enumerate(targets):
+            cost_matrix[i, :] = self._metric(self.samples[target], features)
+        return cost_matrix

yolov5/deep_sort_pytorch/deep_sort/sort/preprocessing.py

@@ -0,0 +1,73 @@
+# vim: expandtab:ts=4:sw=4
+import numpy as np
+import cv2
+
+
+def non_max_suppression(boxes, max_bbox_overlap, scores=None):
+    """Suppress overlapping detections.
+
+    Original code from [1]_ has been adapted to include confidence score.
+
+    .. [1] http://www.pyimagesearch.com/2015/02/16/
+           faster-non-maximum-suppression-python/
+
+    Examples
+    --------
+
+        >>> boxes = [d.roi for d in detections]
+        >>> scores = [d.confidence for d in detections]
+        >>> indices = non_max_suppression(boxes, max_bbox_overlap, scores)
+        >>> detections = [detections[i] for i in indices]
+
+    Parameters
+    ----------
+    boxes : ndarray
+        Array of ROIs (x, y, width, height).
+    max_bbox_overlap : float
+        ROIs that overlap more than this values are suppressed.
+    scores : Optional[array_like]
+        Detector confidence score.
+
+    Returns
+    -------
+    List[int]
+        Returns indices of detections that have survived non-maxima suppression.
+
+    """
+    if len(boxes) == 0:
+        return []
+
+    boxes = boxes.astype(np.float)
+    pick = []
+
+    x1 = boxes[:, 0]
+    y1 = boxes[:, 1]
+    x2 = boxes[:, 2] + boxes[:, 0]
+    y2 = boxes[:, 3] + boxes[:, 1]
+
+    area = (x2 - x1 + 1) * (y2 - y1 + 1)
+    if scores is not None:
+        idxs = np.argsort(scores)
+    else:
+        idxs = np.argsort(y2)
+
+    while len(idxs) > 0:
+        last = len(idxs) - 1
+        i = idxs[last]
+        pick.append(i)
+
+        xx1 = np.maximum(x1[i], x1[idxs[:last]])
+        yy1 = np.maximum(y1[i], y1[idxs[:last]])
+        xx2 = np.minimum(x2[i], x2[idxs[:last]])
+        yy2 = np.minimum(y2[i], y2[idxs[:last]])
+
+        w = np.maximum(0, xx2 - xx1 + 1)
+        h = np.maximum(0, yy2 - yy1 + 1)
+
+        overlap = (w * h) / area[idxs[:last]]
+
+        idxs = np.delete(
+            idxs, np.concatenate(
+                ([last], np.where(overlap > max_bbox_overlap)[0])))
+
+    return pick

yolov5/deep_sort_pytorch/deep_sort/sort/track.py

@@ -0,0 +1,169 @@
+# vim: expandtab:ts=4:sw=4
+
+
+class TrackState:
+    """
+    Enumeration type for the single target track state. Newly created tracks are
+    classified as `tentative` until enough evidence has been collected. Then,
+    the track state is changed to `confirmed`. Tracks that are no longer alive
+    are classified as `deleted` to mark them for removal from the set of active
+    tracks.
+
+    """
+
+    Tentative = 1
+    Confirmed = 2
+    Deleted = 3
+
+
+class Track:
+    """
+    A single target track with state space `(x, y, a, h)` and associated
+    velocities, where `(x, y)` is the center of the bounding box, `a` is the
+    aspect ratio and `h` is the height.
+
+    Parameters
+    ----------
+    mean : ndarray
+        Mean vector of the initial state distribution.
+    covariance : ndarray
+        Covariance matrix of the initial state distribution.
+    track_id : int
+        A unique track identifier.
+    n_init : int
+        Number of consecutive detections before the track is confirmed. The
+        track state is set to `Deleted` if a miss occurs within the first
+        `n_init` frames.
+    max_age : int
+        The maximum number of consecutive misses before the track state is
+        set to `Deleted`.
+    feature : Optional[ndarray]
+        Feature vector of the detection this track originates from. If not None,
+        this feature is added to the `features` cache.
+
+    Attributes
+    ----------
+    mean : ndarray
+        Mean vector of the initial state distribution.
+    covariance : ndarray
+        Covariance matrix of the initial state distribution.
+    track_id : int
+        A unique track identifier.
+    hits : int
+        Total number of measurement updates.
+    age : int
+        Total number of frames since first occurance.
+    time_since_update : int
+        Total number of frames since last measurement update.
+    state : TrackState
+        The current track state.
+    features : List[ndarray]
+        A cache of features. On each measurement update, the associated feature
+        vector is added to this list.
+
+    """
+
+    def __init__(self, mean, covariance, track_id, n_init, max_age,
+                 feature=None):
+        self.mean = mean
+        self.covariance = covariance
+        self.track_id = track_id
+        self.hits = 1
+        self.age = 1
+        self.time_since_update = 0
+
+        self.state = TrackState.Tentative
+        self.features = []
+        if feature is not None:
+            self.features.append(feature)
+
+        self._n_init = n_init
+        self._max_age = max_age
+
+    def to_tlwh(self):
+        """Get current position in bounding box format `(top left x, top left y,
+        width, height)`.
+
+        Returns
+        -------
+        ndarray
+            The bounding box.
+
+        """
+        ret = self.mean[:4].copy()
+        ret[2] *= ret[3]
+        ret[:2] -= ret[2:] / 2
+        return ret
+
+    def to_tlbr(self):
+        """Get current position in bounding box format `(min x, miny, max x,
+        max y)`.
+
+        Returns
+        -------
+        ndarray
+            The bounding box.
+
+        """
+        ret = self.to_tlwh()
+        ret[2:] = ret[:2] + ret[2:]
+        return ret
+
+    def increment_age(self):
+        self.age += 1
+        self.time_since_update += 1
+
+    def predict(self, kf):
+        """Propagate the state distribution to the current time step using a
+        Kalman filter prediction step.
+
+        Parameters
+        ----------
+        kf : kalman_filter.KalmanFilter
+            The Kalman filter.
+
+        """
+        self.mean, self.covariance = kf.predict(self.mean, self.covariance)
+        self.increment_age()
+
+    def update(self, kf, detection):
+        """Perform Kalman filter measurement update step and update the feature
+        cache.
+
+        Parameters
+        ----------
+        kf : kalman_filter.KalmanFilter
+            The Kalman filter.
+        detection : Detection
+            The associated detection.
+
+        """
+        self.mean, self.covariance = kf.update(
+            self.mean, self.covariance, detection.to_xyah())
+        self.features.append(detection.feature)
+
+        self.hits += 1
+        self.time_since_update = 0
+        if self.state == TrackState.Tentative and self.hits >= self._n_init:
+            self.state = TrackState.Confirmed
+
+    def mark_missed(self):
+        """Mark this track as missed (no association at the current time step).
+        """
+        if self.state == TrackState.Tentative:
+            self.state = TrackState.Deleted
+        elif self.time_since_update > self._max_age:
+            self.state = TrackState.Deleted
+
+    def is_tentative(self):
+        """Returns True if this track is tentative (unconfirmed).
+        """
+        return self.state == TrackState.Tentative
+
+    def is_confirmed(self):
+        """Returns True if this track is confirmed."""
+        return self.state == TrackState.Confirmed
+
+    def is_deleted(self):
+        """Returns True if this track is dead and should be deleted."""
+        return self.state == TrackState.Deleted

yolov5/deep_sort_pytorch/deep_sort/sort/tracker.py

@@ -0,0 +1,143 @@
+# vim: expandtab:ts=4:sw=4
+from __future__ import absolute_import
+import numpy as np
+from . import kalman_filter
+from . import linear_assignment
+from . import iou_matching
+from .track import Track
+
+
+class Tracker:
+    """
+    This is the multi-target tracker.
+
+    Parameters
+    ----------
+    metric : nn_matching.NearestNeighborDistanceMetric
+        A distance metric for measurement-to-track association.
+    max_age : int
+        Maximum number of missed misses before a track is deleted.
+    n_init : int
+        Number of consecutive detections before the track is confirmed. The
+        track state is set to `Deleted` if a miss occurs within the first
+        `n_init` frames.
+
+    Attributes
+    ----------
+    metric : nn_matching.NearestNeighborDistanceMetric
+        The distance metric used for measurement to track association.
+    max_age : int
+        Maximum number of missed misses before a track is deleted.
+    n_init : int
+        Number of frames that a track remains in initialization phase.
+    kf : kalman_filter.KalmanFilter
+        A Kalman filter to filter target trajectories in image space.
+    tracks : List[Track]
+        The list of active tracks at the current time step.
+
+    """
+
+    def __init__(self, metric, max_iou_distance=0.7, max_age=70, n_init=3):
+        self.metric = metric
+        self.max_iou_distance = max_iou_distance
+        self.max_age = max_age
+        self.n_init = n_init
+
+        self.kf = kalman_filter.KalmanFilter()
+        self.tracks = []
+        self._next_id = 1
+
+    def predict(self):
+        """Propagate track state distributions one time step forward.
+
+        This function should be called once every time step, before `update`.
+        """
+        for track in self.tracks:
+            track.predict(self.kf)
+
+    def increment_ages(self):
+        for track in self.tracks:
+            track.increment_age()
+            track.mark_missed()
+
+    def update(self, detections):
+        """Perform measurement update and track management.
+
+        Parameters
+        ----------
+        detections : List[deep_sort.detection.Detection]
+            A list of detections at the current time step.
+
+        """
+        # Run matching cascade.
+        matches, unmatched_tracks, unmatched_detections = \
+            self._match(detections)
+
+        # Update track set.
+        for track_idx, detection_idx in matches:
+            self.tracks[track_idx].update(
+                self.kf, detections[detection_idx])
+        for track_idx in unmatched_tracks:
+            self.tracks[track_idx].mark_missed()
+        for detection_idx in unmatched_detections:
+            self._initiate_track(detections[detection_idx])
+        self.tracks = [t for t in self.tracks if not t.is_deleted()]
+
+        # Update distance metric.
+        active_targets = [t.track_id for t in self.tracks if t.is_confirmed()]
+        features, targets = [], []
+        for track in self.tracks:
+            if not track.is_confirmed():
+                continue
+            features += track.features
+            targets += [track.track_id for _ in track.features]
+            track.features = []
+        self.metric.partial_fit(
+            np.asarray(features), np.asarray(targets), active_targets)
+
+    def _match(self, detections):
+
+        def gated_metric(tracks, dets, track_indices, detection_indices):
+            features = np.array([dets[i].feature for i in detection_indices])
+            targets = np.array([tracks[i].track_id for i in track_indices])
+            cost_matrix = self.metric.distance(features, targets)
+            cost_matrix = linear_assignment.gate_cost_matrix(
+                self.kf, cost_matrix, tracks, dets, track_indices,
+                detection_indices)
+
+            return cost_matrix
+
+        # Split track set into confirmed and unconfirmed tracks.
+        confirmed_tracks = [
+            i for i, t in enumerate(self.tracks) if t.is_confirmed()]
+        unconfirmed_tracks = [
+            i for i, t in enumerate(self.tracks) if not t.is_confirmed()]
+
+        # Associate confirmed tracks using appearance features.
+        matches_a, unmatched_tracks_a, unmatched_detections = \
+            linear_assignment.matching_cascade(
+                gated_metric, self.metric.matching_threshold, self.max_age,
+                self.tracks, detections, confirmed_tracks)
+
+        # Associate remaining tracks together with unconfirmed tracks using IOU.
+        iou_track_candidates = unconfirmed_tracks + [
+            k for k in unmatched_tracks_a if
+            self.tracks[k].time_since_update == 1]
+        unmatched_tracks_a = [
+            k for k in unmatched_tracks_a if
+            self.tracks[k].time_since_update != 1]
+        matches_b, unmatched_tracks_b, unmatched_detections = \
+            linear_assignment.min_cost_matching(
+                iou_matching.iou_cost, self.max_iou_distance, self.tracks,
+                detections, iou_track_candidates, unmatched_detections)
+
+        matches = matches_a + matches_b
+        unmatched_tracks = list(set(unmatched_tracks_a + unmatched_tracks_b))
+        return matches, unmatched_tracks, unmatched_detections
+
+    def _initiate_track(self, detection):
+        mean, covariance = self.kf.initiate(detection.to_xyah())
+        self.tracks.append(Track(
+            mean, covariance, self._next_id, self.n_init, self.max_age,
+            detection.feature))
+        self._next_id += 1

yolov5/deep_sort_pytorch/utils/asserts.py

@@ -0,0 +1,13 @@
+from os import environ
+
+
+def assert_in(file, files_to_check):
+    if file not in files_to_check:
+        raise AssertionError("{} does not exist in the list".format(str(file)))
+    return True
+
+
+def assert_in_env(check_list: list):
+    for item in check_list:
+        assert_in(item, environ.keys())
+    return True

yolov5/deep_sort_pytorch/utils/draw.py

@@ -0,0 +1,36 @@
+import numpy as np
+import cv2
+
+palette = (2 ** 11 - 1, 2 ** 15 - 1, 2 ** 20 - 1)
+
+
+def compute_color_for_labels(label):
+    """
+    Simple function that adds fixed color depending on the class
+    """
+    color = [int((p * (label ** 2 - label + 1)) % 255) for p in palette]
+    return tuple(color)
+
+
+def draw_boxes(img, bbox, identities=None, offset=(0,0)):
+    for i,box in enumerate(bbox):
+        x1,y1,x2,y2 = [int(i) for i in box]
+        x1 += offset[0]
+        x2 += offset[0]
+        y1 += offset[1]
+        y2 += offset[1]
+        # box text and bar
+        id = int(identities[i]) if identities is not None else 0    
+        color = compute_color_for_labels(id)
+        label = '{}{:d}'.format("", id)
+        t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2 , 2)[0]
+        cv2.rectangle(img,(x1, y1),(x2,y2),color,3)
+        cv2.rectangle(img,(x1, y1),(x1+t_size[0]+3,y1+t_size[1]+4), color,-1)
+        cv2.putText(img,label,(x1,y1+t_size[1]+4), cv2.FONT_HERSHEY_PLAIN, 2, [255,255,255], 2)
+    return img
+
+
+
+if __name__ == '__main__':
+    for i in range(82):
+        print(compute_color_for_labels(i))

yolov5/deep_sort_pytorch/utils/evaluation.py

@@ -0,0 +1,103 @@
+import os
+import numpy as np
+import copy
+import motmetrics as mm
+mm.lap.default_solver = 'lap'
+from utils.io import read_results, unzip_objs
+
+
+class Evaluator(object):
+
+    def __init__(self, data_root, seq_name, data_type):
+        self.data_root = data_root
+        self.seq_name = seq_name
+        self.data_type = data_type
+
+        self.load_annotations()
+        self.reset_accumulator()
+
+    def load_annotations(self):
+        assert self.data_type == 'mot'
+
+        gt_filename = os.path.join(self.data_root, self.seq_name, 'gt', 'gt.txt')
+        self.gt_frame_dict = read_results(gt_filename, self.data_type, is_gt=True)
+        self.gt_ignore_frame_dict = read_results(gt_filename, self.data_type, is_ignore=True)
+
+    def reset_accumulator(self):
+        self.acc = mm.MOTAccumulator(auto_id=True)
+
+    def eval_frame(self, frame_id, trk_tlwhs, trk_ids, rtn_events=False):
+        # results
+        trk_tlwhs = np.copy(trk_tlwhs)
+        trk_ids = np.copy(trk_ids)
+
+        # gts
+        gt_objs = self.gt_frame_dict.get(frame_id, [])
+        gt_tlwhs, gt_ids = unzip_objs(gt_objs)[:2]
+
+        # ignore boxes
+        ignore_objs = self.gt_ignore_frame_dict.get(frame_id, [])
+        ignore_tlwhs = unzip_objs(ignore_objs)[0]
+
+
+        # remove ignored results
+        keep = np.ones(len(trk_tlwhs), dtype=bool)
+        iou_distance = mm.distances.iou_matrix(ignore_tlwhs, trk_tlwhs, max_iou=0.5)
+        if len(iou_distance) > 0:
+            match_is, match_js = mm.lap.linear_sum_assignment(iou_distance)
+            match_is, match_js = map(lambda a: np.asarray(a, dtype=int), [match_is, match_js])
+            match_ious = iou_distance[match_is, match_js]
+
+            match_js = np.asarray(match_js, dtype=int)
+            match_js = match_js[np.logical_not(np.isnan(match_ious))]
+            keep[match_js] = False
+            trk_tlwhs = trk_tlwhs[keep]
+            trk_ids = trk_ids[keep]
+
+        # get distance matrix
+        iou_distance = mm.distances.iou_matrix(gt_tlwhs, trk_tlwhs, max_iou=0.5)
+
+        # acc
+        self.acc.update(gt_ids, trk_ids, iou_distance)
+
+        if rtn_events and iou_distance.size > 0 and hasattr(self.acc, 'last_mot_events'):
+            events = self.acc.last_mot_events  # only supported by https://github.com/longcw/py-motmetrics
+        else:
+            events = None
+        return events
+
+    def eval_file(self, filename):
+        self.reset_accumulator()
+
+        result_frame_dict = read_results(filename, self.data_type, is_gt=False)
+        frames = sorted(list(set(self.gt_frame_dict.keys()) | set(result_frame_dict.keys())))
+        for frame_id in frames:
+            trk_objs = result_frame_dict.get(frame_id, [])
+            trk_tlwhs, trk_ids = unzip_objs(trk_objs)[:2]
+            self.eval_frame(frame_id, trk_tlwhs, trk_ids, rtn_events=False)
+
+        return self.acc
+
+    @staticmethod
+    def get_summary(accs, names, metrics=('mota', 'num_switches', 'idp', 'idr', 'idf1', 'precision', 'recall')):
+        names = copy.deepcopy(names)
+        if metrics is None:
+            metrics = mm.metrics.motchallenge_metrics
+        metrics = copy.deepcopy(metrics)
+
+        mh = mm.metrics.create()
+        summary = mh.compute_many(
+            accs,
+            metrics=metrics,
+            names=names,
+            generate_overall=True
+        )
+
+        return summary
+
+    @staticmethod
+    def save_summary(summary, filename):
+        import pandas as pd
+        writer = pd.ExcelWriter(filename)
+        summary.to_excel(writer)
+        writer.save()

yolov5/deep_sort_pytorch/utils/io.py

@@ -0,0 +1,133 @@
+import os
+from typing import Dict
+import numpy as np
+
+# from utils.log import get_logger
+
+
+def write_results(filename, results, data_type):
+    if data_type == 'mot':
+        save_format = '{frame},{id},{x1},{y1},{w},{h},-1,-1,-1,-1\n'
+    elif data_type == 'kitti':
+        save_format = '{frame} {id} pedestrian 0 0 -10 {x1} {y1} {x2} {y2} -10 -10 -10 -1000 -1000 -1000 -10\n'
+    else:
+        raise ValueError(data_type)
+
+    with open(filename, 'w') as f:
+        for frame_id, tlwhs, track_ids in results:
+            if data_type == 'kitti':
+                frame_id -= 1
+            for tlwh, track_id in zip(tlwhs, track_ids):
+                if track_id < 0:
+                    continue
+                x1, y1, w, h = tlwh
+                x2, y2 = x1 + w, y1 + h
+                line = save_format.format(frame=frame_id, id=track_id, x1=x1, y1=y1, x2=x2, y2=y2, w=w, h=h)
+                f.write(line)
+
+
+# def write_results(filename, results_dict: Dict, data_type: str):
+#     if not filename:
+#         return
+#     path = os.path.dirname(filename)
+#     if not os.path.exists(path):
+#         os.makedirs(path)
+
+#     if data_type in ('mot', 'mcmot', 'lab'):
+#         save_format = '{frame},{id},{x1},{y1},{w},{h},1,-1,-1,-1\n'
+#     elif data_type == 'kitti':
+#         save_format = '{frame} {id} pedestrian -1 -1 -10 {x1} {y1} {x2} {y2} -1 -1 -1 -1000 -1000 -1000 -10 {score}\n'
+#     else:
+#         raise ValueError(data_type)
+
+#     with open(filename, 'w') as f:
+#         for frame_id, frame_data in results_dict.items():
+#             if data_type == 'kitti':
+#                 frame_id -= 1
+#             for tlwh, track_id in frame_data:
+#                 if track_id < 0:
+#                     continue
+#                 x1, y1, w, h = tlwh
+#                 x2, y2 = x1 + w, y1 + h
+#                 line = save_format.format(frame=frame_id, id=track_id, x1=x1, y1=y1, x2=x2, y2=y2, w=w, h=h, score=1.0)
+#                 f.write(line)
+#     logger.info('Save results to {}'.format(filename))
+
+
+def read_results(filename, data_type: str, is_gt=False, is_ignore=False):
+    if data_type in ('mot', 'lab'):
+        read_fun = read_mot_results
+    else:
+        raise ValueError('Unknown data type: {}'.format(data_type))
+
+    return read_fun(filename, is_gt, is_ignore)
+
+
+"""
+labels={'ped', ...			% 1
+'person_on_vhcl', ...	% 2
+'car', ...				% 3
+'bicycle', ...			% 4
+'mbike', ...			% 5
+'non_mot_vhcl', ...		% 6
+'static_person', ...	% 7
+'distractor', ...		% 8
+'occluder', ...			% 9
+'occluder_on_grnd', ...		%10
+'occluder_full', ...		% 11
+'reflection', ...		% 12
+'crowd' ...			% 13
+};
+"""
+
+
+def read_mot_results(filename, is_gt, is_ignore):
+    valid_labels = {1}
+    ignore_labels = {2, 7, 8, 12}
+    results_dict = dict()
+    if os.path.isfile(filename):
+        with open(filename, 'r') as f:
+            for line in f.readlines():
+                linelist = line.split(',')
+                if len(linelist) < 7:
+                    continue
+                fid = int(linelist[0])
+                if fid < 1:
+                    continue
+                results_dict.setdefault(fid, list())
+
+                if is_gt:
+                    if 'MOT16-' in filename or 'MOT17-' in filename:
+                        label = int(float(linelist[7]))
+                        mark = int(float(linelist[6]))
+                        if mark == 0 or label not in valid_labels:
+                            continue
+                    score = 1
+                elif is_ignore:
+                    if 'MOT16-' in filename or 'MOT17-' in filename:
+                        label = int(float(linelist[7]))
+                        vis_ratio = float(linelist[8])
+                        if label not in ignore_labels and vis_ratio >= 0:
+                            continue
+                    else:
+                        continue
+                    score = 1
+                else:
+                    score = float(linelist[6])
+
+                tlwh = tuple(map(float, linelist[2:6]))
+                target_id = int(linelist[1])
+
+                results_dict[fid].append((tlwh, target_id, score))
+
+    return results_dict
+
+
+def unzip_objs(objs):
+    if len(objs) > 0:
+        tlwhs, ids, scores = zip(*objs)
+    else:
+        tlwhs, ids, scores = [], [], []
+    tlwhs = np.asarray(tlwhs, dtype=float).reshape(-1, 4)
+
+    return tlwhs, ids, scores

yolov5/deep_sort_pytorch/utils/json_logger.py

@@ -0,0 +1,383 @@
+"""
+References:
+    https://medium.com/analytics-vidhya/creating-a-custom-logging-mechanism-for-real-time-object-detection-using-tdd-4ca2cfcd0a2f
+"""
+import json
+from os import makedirs
+from os.path import exists, join
+from datetime import datetime
+
+
+class JsonMeta(object):
+    HOURS = 3
+    MINUTES = 59
+    SECONDS = 59
+    PATH_TO_SAVE = 'LOGS'
+    DEFAULT_FILE_NAME = 'remaining'
+
+
+class BaseJsonLogger(object):
+    """
+    This is the base class that returns __dict__ of its own
+    it also returns the dicts of objects in the attributes that are list instances
+
+    """
+
+    def dic(self):
+        # returns dicts of objects
+        out = {}
+        for k, v in self.__dict__.items():
+            if hasattr(v, 'dic'):
+                out[k] = v.dic()
+            elif isinstance(v, list):
+                out[k] = self.list(v)
+            else:
+                out[k] = v
+        return out
+
+    @staticmethod
+    def list(values):
+        # applies the dic method on items in the list
+        return [v.dic() if hasattr(v, 'dic') else v for v in values]
+
+
+class Label(BaseJsonLogger):
+    """
+    For each bounding box there are various categories with confidences. Label class keeps track of that information.
+    """
+
+    def __init__(self, category: str, confidence: float):
+        self.category = category
+        self.confidence = confidence
+
+
+class Bbox(BaseJsonLogger):
+    """
+    This module stores the information for each frame and use them in JsonParser
+    Attributes:
+        labels (list): List of label module.
+        top (int):
+        left (int):
+        width (int):
+        height (int):
+
+    Args:
+        bbox_id (float):
+        top (int):
+        left (int):
+        width (int):
+        height (int):
+
+    References:
+        Check Label module for better understanding.
+
+
+    """
+
+    def __init__(self, bbox_id, top, left, width, height):
+        self.labels = []
+        self.bbox_id = bbox_id
+        self.top = top
+        self.left = left
+        self.width = width
+        self.height = height
+
+    def add_label(self, category, confidence):
+        # adds category and confidence only if top_k is not exceeded.
+        self.labels.append(Label(category, confidence))
+
+    def labels_full(self, value):
+        return len(self.labels) == value
+
+
+class Frame(BaseJsonLogger):
+    """
+    This module stores the information for each frame and use them in JsonParser
+    Attributes:
+        timestamp (float): The elapsed time of captured frame
+        frame_id (int): The frame number of the captured video
+        bboxes (list of Bbox objects): Stores the list of bbox objects.
+
+    References:
+        Check Bbox class for better information
+
+    Args:
+        timestamp (float):
+        frame_id (int):
+
+    """
+
+    def __init__(self, frame_id: int, timestamp: float = None):
+        self.frame_id = frame_id
+        self.timestamp = timestamp
+        self.bboxes = []
+
+    def add_bbox(self, bbox_id: int, top: int, left: int, width: int, height: int):
+        bboxes_ids = [bbox.bbox_id for bbox in self.bboxes]
+        if bbox_id not in bboxes_ids:
+            self.bboxes.append(Bbox(bbox_id, top, left, width, height))
+        else:
+            raise ValueError("Frame with id: {} already has a Bbox with id: {}".format(self.frame_id, bbox_id))
+
+    def add_label_to_bbox(self, bbox_id: int, category: str, confidence: float):
+        bboxes = {bbox.id: bbox for bbox in self.bboxes}
+        if bbox_id in bboxes.keys():
+            res = bboxes.get(bbox_id)
+            res.add_label(category, confidence)
+        else:
+            raise ValueError('the bbox with id: {} does not exists!'.format(bbox_id))
+
+
+class BboxToJsonLogger(BaseJsonLogger):
+    """
+    ُ This module is designed to automate the task of logging jsons. An example json is used
+    to show the contents of json file shortly
+    Example:
+          {
+          "video_details": {
+            "frame_width": 1920,
+            "frame_height": 1080,
+            "frame_rate": 20,
+            "video_name": "/home/gpu/codes/MSD/pedestrian_2/project/public/camera1.avi"
+          },
+          "frames": [
+            {
+              "frame_id": 329,
+              "timestamp": 3365.1254
+              "bboxes": [
+                {
+                  "labels": [
+                    {
+                      "category": "pedestrian",
+                      "confidence": 0.9
+                    }
+                  ],
+                  "bbox_id": 0,
+                  "top": 1257,
+                  "left": 138,
+                  "width": 68,
+                  "height": 109
+                }
+              ]
+            }],
+
+    Attributes:
+        frames (dict): It's a dictionary that maps each frame_id to json attributes.
+        video_details (dict): information about video file.
+        top_k_labels (int): shows the allowed number of labels
+        start_time (datetime object): we use it to automate the json output by time.
+
+    Args:
+        top_k_labels (int): shows the allowed number of labels
+
+    """
+
+    def __init__(self, top_k_labels: int = 1):
+        self.frames = {}
+        self.video_details = self.video_details = dict(frame_width=None, frame_height=None, frame_rate=None,
+                                                       video_name=None)
+        self.top_k_labels = top_k_labels
+        self.start_time = datetime.now()
+
+    def set_top_k(self, value):
+        self.top_k_labels = value
+
+    def frame_exists(self, frame_id: int) -> bool:
+        """
+        Args:
+            frame_id (int):
+
+        Returns:
+            bool: true if frame_id is recognized
+        """
+        return frame_id in self.frames.keys()
+
+    def add_frame(self, frame_id: int, timestamp: float = None) -> None:
+        """
+        Args:
+            frame_id (int):
+            timestamp (float): opencv captured frame time property
+
+        Raises:
+             ValueError: if frame_id would not exist in class frames attribute
+
+        Returns:
+            None
+
+        """
+        if not self.frame_exists(frame_id):
+            self.frames[frame_id] = Frame(frame_id, timestamp)
+        else:
+            raise ValueError("Frame id: {} already exists".format(frame_id))
+
+    def bbox_exists(self, frame_id: int, bbox_id: int) -> bool:
+        """
+        Args:
+            frame_id:
+            bbox_id:
+
+        Returns:
+            bool: if bbox exists in frame bboxes list
+        """
+        bboxes = []
+        if self.frame_exists(frame_id=frame_id):
+            bboxes = [bbox.bbox_id for bbox in self.frames[frame_id].bboxes]
+        return bbox_id in bboxes
+
+    def find_bbox(self, frame_id: int, bbox_id: int):
+        """
+
+        Args:
+            frame_id:
+            bbox_id:
+
+        Returns:
+            bbox_id (int):
+
+        Raises:
+            ValueError: if bbox_id does not exist in the bbox list of specific frame.
+        """
+        if not self.bbox_exists(frame_id, bbox_id):
+            raise ValueError("frame with id: {} does not contain bbox with id: {}".format(frame_id, bbox_id))
+        bboxes = {bbox.bbox_id: bbox for bbox in self.frames[frame_id].bboxes}
+        return bboxes.get(bbox_id)
+
+    def add_bbox_to_frame(self, frame_id: int, bbox_id: int, top: int, left: int, width: int, height: int) -> None:
+        """
+
+        Args:
+            frame_id (int):
+            bbox_id (int):
+            top (int):
+            left (int):
+            width (int):
+            height (int):
+
+        Returns:
+            None
+
+        Raises:
+            ValueError: if bbox_id already exist in frame information with frame_id
+            ValueError: if frame_id does not exist in frames attribute
+        """
+        if self.frame_exists(frame_id):
+            frame = self.frames[frame_id]
+            if not self.bbox_exists(frame_id, bbox_id):
+                frame.add_bbox(bbox_id, top, left, width, height)
+            else:
+                raise ValueError(
+                    "frame with frame_id: {} already contains the bbox with id: {} ".format(frame_id, bbox_id))
+        else:
+            raise ValueError("frame with frame_id: {} does not exist".format(frame_id))
+
+    def add_label_to_bbox(self, frame_id: int, bbox_id: int, category: str, confidence: float):
+        """
+        Args:
+            frame_id:
+            bbox_id:
+            category:
+            confidence: the confidence value returned from yolo detection
+
+        Returns:
+            None
+
+        Raises:
+            ValueError: if labels quota (top_k_labels) exceeds.
+        """
+        bbox = self.find_bbox(frame_id, bbox_id)
+        if not bbox.labels_full(self.top_k_labels):
+            bbox.add_label(category, confidence)
+        else:
+            raise ValueError("labels in frame_id: {}, bbox_id: {} is fulled".format(frame_id, bbox_id))
+
+    def add_video_details(self, frame_width: int = None, frame_height: int = None, frame_rate: int = None,
+                          video_name: str = None):
+        self.video_details['frame_width'] = frame_width
+        self.video_details['frame_height'] = frame_height
+        self.video_details['frame_rate'] = frame_rate
+        self.video_details['video_name'] = video_name
+
+    def output(self):
+        output = {'video_details': self.video_details}
+        result = list(self.frames.values())
+        output['frames'] = [item.dic() for item in result]
+        return output
+
+    def json_output(self, output_name):
+        """
+        Args:
+            output_name:
+
+        Returns:
+            None
+
+        Notes:
+            It creates the json output with `output_name` name.
+        """
+        if not output_name.endswith('.json'):
+            output_name += '.json'
+        with open(output_name, 'w') as file:
+            json.dump(self.output(), file)
+        file.close()
+
+    def set_start(self):
+        self.start_time = datetime.now()
+
+    def schedule_output_by_time(self, output_dir=JsonMeta.PATH_TO_SAVE, hours: int = 0, minutes: int = 0,
+                                seconds: int = 60) -> None:
+        """
+        Notes:
+            Creates folder and then periodically stores the jsons on that address.
+
+        Args:
+            output_dir (str): the directory where output files will be stored
+            hours (int):
+            minutes (int):
+            seconds (int):
+
+        Returns:
+            None
+
+        """
+        end = datetime.now()
+        interval = 0
+        interval += abs(min([hours, JsonMeta.HOURS]) * 3600)
+        interval += abs(min([minutes, JsonMeta.MINUTES]) * 60)
+        interval += abs(min([seconds, JsonMeta.SECONDS]))
+        diff = (end - self.start_time).seconds
+
+        if diff > interval:
+            output_name = self.start_time.strftime('%Y-%m-%d %H-%M-%S') + '.json'
+            if not exists(output_dir):
+                makedirs(output_dir)
+            output = join(output_dir, output_name)
+            self.json_output(output_name=output)
+            self.frames = {}
+            self.start_time = datetime.now()
+
+    def schedule_output_by_frames(self, frames_quota, frame_counter, output_dir=JsonMeta.PATH_TO_SAVE):
+        """
+        saves as the number of frames quota increases higher.
+        :param frames_quota:
+        :param frame_counter:
+        :param output_dir:
+        :return:
+        """
+        pass
+
+    def flush(self, output_dir):
+        """
+        Notes:
+            We use this function to output jsons whenever possible.
+            like the time that we exit the while loop of opencv.
+
+        Args:
+            output_dir:
+
+        Returns:
+            None
+
+        """
+        filename = self.start_time.strftime('%Y-%m-%d %H-%M-%S') + '-remaining.json'
+        output = join(output_dir, filename)
+        self.json_output(output_name=output)

yolov5/deep_sort_pytorch/utils/log.py

@@ -0,0 +1,17 @@
+import logging
+
+
+def get_logger(name='root'):
+    formatter = logging.Formatter(
+        # fmt='%(asctime)s [%(levelname)s]: %(filename)s(%(funcName)s:%(lineno)s) >> %(message)s')
+        fmt='%(asctime)s [%(levelname)s]: %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
+
+    handler = logging.StreamHandler()
+    handler.setFormatter(formatter)
+
+    logger = logging.getLogger(name)
+    logger.setLevel(logging.INFO)
+    logger.addHandler(handler)
+    return logger
+
+

yolov5/deep_sort_pytorch/utils/parser.py

@@ -0,0 +1,39 @@
+import os
+import yaml
+from easydict import EasyDict as edict
+
+
+class YamlParser(edict):
+    """
+    This is yaml parser based on EasyDict.
+    """
+
+    def __init__(self, cfg_dict=None, config_file=None):
+        if cfg_dict is None:
+            cfg_dict = {}
+
+        if config_file is not None:
+            assert(os.path.isfile(config_file))
+            with open(config_file, 'r') as fo:
+                cfg_dict.update(yaml.load(fo.read()))
+
+        super(YamlParser, self).__init__(cfg_dict)
+
+    def merge_from_file(self, config_file):
+        with open(config_file, 'r') as fo:
+            self.update(yaml.load(fo.read()))
+
+    def merge_from_dict(self, config_dict):
+        self.update(config_dict)
+
+
+def get_config(config_file=None):
+    return YamlParser(config_file=config_file)
+
+
+if __name__ == "__main__":
+    cfg = YamlParser(config_file="../configs/yolov3.yaml")
+    cfg.merge_from_file("../configs/deep_sort.yaml")
+
+    import ipdb
+    ipdb.set_trace()

yolov5/deep_sort_pytorch/utils/tools.py

@@ -0,0 +1,39 @@
+from functools import wraps
+from time import time
+
+
+def is_video(ext: str):
+    """
+    Returns true if ext exists in
+    allowed_exts for video files.
+
+    Args:
+        ext:
+
+    Returns:
+
+    """
+
+    allowed_exts = ('.mp4', '.webm', '.ogg', '.avi', '.wmv', '.mkv', '.3gp')
+    return any((ext.endswith(x) for x in allowed_exts))
+
+
+def tik_tok(func):
+    """
+    keep track of time for each process.
+    Args:
+        func:
+
+    Returns:
+
+    """
+    @wraps(func)
+    def _time_it(*args, **kwargs):
+        start = time()
+        try:
+            return func(*args, **kwargs)
+        finally:
+            end_ = time()
+            print("time: {:.03f}s, fps: {:.03f}".format(end_ - start, 1 / (end_ - start)))
+
+    return _time_it

yolov5/detect.py

@@ -0,0 +1,276 @@
+import argparse
+import time
+import os
+from pathlib import Path
+
+import cv2
+import sklearn
+import torch
+import torch.backends.cudnn as cudnn
+import numpy as np
+from numpy import random
+
+from models.experimental import attempt_load
+from utils.datasets import LoadStreams, LoadImages
+from utils.general import check_img_size, non_max_suppression, apply_classifier, scale_coords, xyxy2xywh, \
+    strip_optimizer, set_logging, increment_path
+from utils.plots import plot_one_box
+from utils.torch_utils import select_device, load_classifier, time_synchronized
+from deep_sort_pytorch.utils.parser import get_config
+from deep_sort_pytorch.deep_sort import DeepSort
+
+import player
+
+def bbox_rel(*xyxy):
+    """" Calculates the relative bounding box from absolute pixel values. """
+    bbox_left = min([xyxy[0].item(), xyxy[2].item()])
+    bbox_top = min([xyxy[1].item(), xyxy[3].item()])
+    bbox_w = abs(xyxy[0].item() - xyxy[2].item())
+    bbox_h = abs(xyxy[1].item() - xyxy[3].item())
+    x_c = (bbox_left + bbox_w / 2)
+    y_c = (bbox_top + bbox_h / 2)
+    w = bbox_w
+    h = bbox_h
+    return x_c, y_c, w, h
+
+
+players = {}
+
+
+def draw_boxes(img, bbox, identities=None, offset=(0, 0)):
+    for i, box in enumerate(bbox):
+        x1, y1, x2, y2 = [int(i) for i in box]
+        x1 += offset[0]
+        x2 += offset[0]
+        y1 += offset[1]
+        y2 += offset[1]
+        # box text and bar
+        id = int(identities[i]) if identities is not None else 0
+        if id in players.keys():
+            current_player = players.get(id)
+            # only if checking colors automatically:
+            current_player.assignTeam(players)
+            label = current_player.team
+        else:
+            # check color manually
+            # team, color = player.check_color_manual2(left_clicks,img,x1,x2,y1,y2)
+
+            # check color automatically
+            color = player.detectPlayerColor(img,x1,x2,y1,y2)
+
+            current_player = player.Player(id,color=color,x=x2-(x2-x1),y=y2)
+            label = "?"
+            players[id] = current_player
+            
+        # label = current_player.team
+        plot_one_box(box, img, label=label, color=(int(current_player.color[0]), int(current_player.color[1]), int(current_player.color[2])), line_thickness=1)
+        #plot_one_box(box, img, label=label, color=current_player.color, line_thickness=1)
+   
+    return img
+
+
+def detect(save_img=False):
+    source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
+    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
+        ('rtsp://', 'rtmp://', 'http://'))
+
+    # Directories
+    save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run
+    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+
+    # DeepSort Initialize
+    cfg = get_config()
+    cfg.merge_from_file(opt.config_deepsort)
+    deepsort = DeepSort(cfg.DEEPSORT.REID_CKPT,
+                        max_dist=cfg.DEEPSORT.MAX_DIST, min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE,
+                        nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE,
+                        max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET,
+                        use_cuda=True)
+
+    # Initialize
+    set_logging()
+    device = select_device(opt.device)
+    half = device.type != 'cpu'  # half precision only supported on CUDA
+
+    # Load model
+    model = attempt_load(weights, map_location=device)  # load FP32 model
+    imgsz = check_img_size(imgsz, s=model.stride.max())  # check img_size
+    if half:
+        model.half()  # to FP16
+
+    # Second-stage classifier
+    classify = False
+    if classify:
+        modelc = load_classifier(name='resnet101', n=2)  # initialize
+        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
+
+    # Set Dataloader
+    vid_path, vid_writer = None, None
+    if webcam:
+        view_img = True
+        cudnn.benchmark = True  # set True to speed up constant image size inference
+        dataset = LoadStreams(source, img_size=imgsz)
+    else:
+        save_img = True
+        dataset = LoadImages(source, img_size=imgsz)
+
+    # Get names
+    names = model.module.names if hasattr(model, 'module') else model.names
+    # Run inference
+    t0 = time.time()
+    img = torch.zeros((1, 3, imgsz, imgsz), device=device)  # init img
+    _ = model(img.half() if half else img) if device.type != 'cpu' else None  # run once
+
+
+    for path, img, im0s, vid_cap in dataset:
+        img = torch.from_numpy(img).to(device)
+        img = img.half() if half else img.float()  # uint8 to fp16/32
+        img /= 255.0  # 0 - 255 to 0.0 - 1.0
+        if img.ndimension() == 3:
+            img = img.unsqueeze(0)
+
+        # Inference
+        t1 = time_synchronized()
+        pred = model(img, augment=opt.augment)[0]
+
+        # Apply NMS
+        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
+        t2 = time_synchronized()
+
+        # Apply Classifier
+        if classify:
+            pred = apply_classifier(pred, modelc, img, im0s)
+        # Process detections
+        for i, det in enumerate(pred):  # detections per image
+            if webcam:  # batch_size >= 1
+                p, s, im0, frame = Path(path[i]), '%g: ' % i, im0s[i].copy(), dataset.count
+            else:
+                p, s, im0, frame = Path(path), '', im0s, getattr(dataset, 'frame', 0)
+
+            save_path = str(save_dir / p.name)
+            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')
+            s += '%gx%g ' % img.shape[2:]  # print string
+            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+            if len(det):
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
+
+                # Print results
+                for c in det[:, -1].unique():
+                    n = (det[:, -1] == c).sum()  # detections per class
+                    s += f'{n} {names[int(c)]}s, '  # add to string
+
+                bbox_xywh = []
+                confs = []
+
+                # Adapt detections to deep sort input format
+                for *xyxy, conf, cls in det:
+                    if cls == 0:
+                        x_c, y_c, bbox_w, bbox_h = bbox_rel(*xyxy)
+                        obj = [x_c, y_c, bbox_w, bbox_h]
+                        bbox_xywh.append(obj)
+                        confs.append([conf.item()])
+
+                xywhs = torch.Tensor(bbox_xywh)
+                confss = torch.Tensor(confs)
+
+                # Pass detections to deepsort
+                outputs = deepsort.update(xywhs, confss, im0)
+
+                # draw boxes for visualization
+                if len(outputs) > 0:
+                    bbox_xyxy = outputs[:, :4]
+                    identities = outputs[:, -1]
+                    draw_boxes(im0, bbox_xyxy, identities)
+                    
+                
+                for *xyxy, conf, cls in reversed(det):
+                    if save_txt:  # Write to file
+                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+                        line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh)  # label format
+                        with open(txt_path + '.txt', 'a') as f:
+                            f.write(('%g ' * len(line)).rstrip() % line + '\n')
+
+                    if cls == 32 and (save_img or view_img):  # Add bbox to ball
+                        #label = f'{names[int(cls)]}'
+                        label = 'ball'
+                        plot_one_box(xyxy, im0, label=label, color=[0,0,0], line_thickness=2)
+
+
+                # Write MOT compliant results to file
+                """ if save_txt and len(outputs) != 0:
+                    for j, output in enumerate(outputs):
+                        bbox_left = output[0]
+                        bbox_top = output[1]
+                        bbox_w = output[2]
+                        bbox_h = output[3]
+                        identity = output[-1]
+                        with open(txt_path + '.txt', 'a') as f:
+                            f.write(('%g ' * 10 + '\n') % (j, identity, bbox_left,
+                                                           bbox_top, bbox_w, bbox_h, -1, -1, -1, -1))  # label format """
+
+            else:
+                deepsort.increment_ages()
+
+            # Print time (inference + NMS)
+            print(f'{s}Done. ({t2 - t1:.3f}s)')
+
+            # Stream results
+            if view_img:
+                cv2.imshow(str(p), im0)
+                if cv2.waitKey(1) == ord('q'):  # q to quit
+                    raise StopIteration
+
+            # Save results (image with detections)
+            if save_img:
+                if dataset.mode == 'image':
+                    cv2.imwrite(save_path, im0)
+                else:  # 'video'
+                    if vid_path != save_path:  # new video
+                        vid_path = save_path
+                        if isinstance(vid_writer, cv2.VideoWriter):
+                            vid_writer.release()  # release previous video writer
+
+                        fourcc = 'mp4v'  # output video codec
+                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h))
+                    vid_writer.write(im0)
+    print(save_path)
+    if save_txt or save_img:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        print(f"Results saved to {save_dir}{s}")
+
+    print(f'Done. ({time.time() - t0:.3f}s)')
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', nargs='+', type=str, default='yolov5l.pt', help='model.pt path(s)')
+    parser.add_argument('--source', type=str, default='data/images', help='source')  # file/folder, 0 for webcam
+    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--view-img', action='store_true', help='display results')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--classes', nargs='+', type=int, default=[0, 32], help='filter by class: --class 0, or --class 0 2 3')
+    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--update', action='store_true', help='update all models')
+    parser.add_argument('--project', default='../win_venv/files/output', help='save results to project/name')
+    parser.add_argument('--name', default='exp', help='save results to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument("--config_deepsort", type=str, default="deep_sort_pytorch/configs/deep_sort.yaml")
+    opt = parser.parse_args()
+    print(opt)
+
+    with torch.no_grad():
+        if opt.update:  # update all models (to fix SourceChangeWarning)
+            for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
+                detect()
+                strip_optimizer(opt.weights)
+        else:
+            detect()

yolov5/hubconf.py

@@ -0,0 +1,141 @@
+"""File for accessing YOLOv5 via PyTorch Hub https://pytorch.org/hub/
+
+Usage:
+    import torch
+    model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True, channels=3, classes=80)
+"""
+
+from pathlib import Path
+
+import torch
+
+from models.yolo import Model
+from utils.general import set_logging
+from utils.google_utils import attempt_download
+
+dependencies = ['torch', 'yaml']
+set_logging()
+
+
+def create(name, pretrained, channels, classes, autoshape):
+    """Creates a specified YOLOv5 model
+
+    Arguments:
+        name (str): name of model, i.e. 'yolov5s'
+        pretrained (bool): load pretrained weights into the model
+        channels (int): number of input channels
+        classes (int): number of model classes
+
+    Returns:
+        pytorch model
+    """
+    config = Path(__file__).parent / 'models' / f'{name}.yaml'  # model.yaml path
+    try:
+        model = Model(config, channels, classes)
+        if pretrained:
+            fname = f'{name}.pt'  # checkpoint filename
+            attempt_download(fname)  # download if not found locally
+            ckpt = torch.load(fname, map_location=torch.device('cpu'))  # load
+            state_dict = ckpt['model'].float().state_dict()  # to FP32
+            state_dict = {k: v for k, v in state_dict.items() if model.state_dict()[k].shape == v.shape}  # filter
+            model.load_state_dict(state_dict, strict=False)  # load
+            if len(ckpt['model'].names) == classes:
+                model.names = ckpt['model'].names  # set class names attribute
+            if autoshape:
+                model = model.autoshape()  # for file/URI/PIL/cv2/np inputs and NMS
+        return model
+
+    except Exception as e:
+        help_url = 'https://github.com/ultralytics/yolov5/issues/36'
+        s = 'Cache maybe be out of date, try force_reload=True. See %s for help.' % help_url
+        raise Exception(s) from e
+
+
+def yolov5s(pretrained=False, channels=3, classes=80, autoshape=True):
+    """YOLOv5-small model from https://github.com/ultralytics/yolov5
+
+    Arguments:
+        pretrained (bool): load pretrained weights into the model, default=False
+        channels (int): number of input channels, default=3
+        classes (int): number of model classes, default=80
+
+    Returns:
+        pytorch model
+    """
+    return create('yolov5s', pretrained, channels, classes, autoshape)
+
+
+def yolov5m(pretrained=False, channels=3, classes=80, autoshape=True):
+    """YOLOv5-medium model from https://github.com/ultralytics/yolov5
+
+    Arguments:
+        pretrained (bool): load pretrained weights into the model, default=False
+        channels (int): number of input channels, default=3
+        classes (int): number of model classes, default=80
+
+    Returns:
+        pytorch model
+    """
+    return create('yolov5m', pretrained, channels, classes, autoshape)
+
+
+def yolov5l(pretrained=False, channels=3, classes=80, autoshape=True):
+    """YOLOv5-large model from https://github.com/ultralytics/yolov5
+
+    Arguments:
+        pretrained (bool): load pretrained weights into the model, default=False
+        channels (int): number of input channels, default=3
+        classes (int): number of model classes, default=80
+
+    Returns:
+        pytorch model
+    """
+    return create('yolov5l', pretrained, channels, classes, autoshape)
+
+
+def yolov5x(pretrained=False, channels=3, classes=80, autoshape=True):
+    """YOLOv5-xlarge model from https://github.com/ultralytics/yolov5
+
+    Arguments:
+        pretrained (bool): load pretrained weights into the model, default=False
+        channels (int): number of input channels, default=3
+        classes (int): number of model classes, default=80
+
+    Returns:
+        pytorch model
+    """
+    return create('yolov5x', pretrained, channels, classes, autoshape)
+
+
+def custom(path_or_model='path/to/model.pt', autoshape=True):
+    """YOLOv5-custom model from https://github.com/ultralytics/yolov5
+
+    Arguments (3 options):
+        path_or_model (str): 'path/to/model.pt'
+        path_or_model (dict): torch.load('path/to/model.pt')
+        path_or_model (nn.Module): torch.load('path/to/model.pt')['model']
+
+    Returns:
+        pytorch model
+    """
+    model = torch.load(path_or_model) if isinstance(path_or_model, str) else path_or_model  # load checkpoint
+    if isinstance(model, dict):
+        model = model['model']  # load model
+
+    hub_model = Model(model.yaml).to(next(model.parameters()).device)  # create
+    hub_model.load_state_dict(model.float().state_dict())  # load state_dict
+    hub_model.names = model.names  # class names
+    return hub_model.autoshape() if autoshape else hub_model
+
+
+if __name__ == '__main__':
+    model = create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True)  # pretrained example
+    # model = custom(path_or_model='path/to/model.pt')  # custom example
+
+    # Verify inference
+    from PIL import Image
+
+    imgs = [Image.open(x) for x in Path('data/images').glob('*.jpg')]
+    results = model(imgs)
+    results.show()
+    results.print()

yolov5/models/common.py

@@ -0,0 +1,273 @@
+# This file contains modules common to various models
+
+import math
+import numpy as np
+import requests
+import torch
+import torch.nn as nn
+from PIL import Image, ImageDraw
+
+from utils.datasets import letterbox
+from utils.general import non_max_suppression, make_divisible, scale_coords, xyxy2xywh
+from utils.plots import color_list
+
+
+def autopad(k, p=None):  # kernel, padding
+    # Pad to 'same'
+    if p is None:
+        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
+    return p
+
+
+def DWConv(c1, c2, k=1, s=1, act=True):
+    # Depthwise convolution
+    return Conv(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
+
+
+class Conv(nn.Module):
+    # Standard convolution
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Conv, self).__init__()
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.Hardswish() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
+
+    def forward(self, x):
+        return self.act(self.bn(self.conv(x)))
+
+    def fuseforward(self, x):
+        return self.act(self.conv(x))
+
+
+class Bottleneck(nn.Module):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super(Bottleneck, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c2, 3, 1, g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class BottleneckCSP(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(BottleneckCSP, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
+        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
+        self.act = nn.LeakyReLU(0.1, inplace=True)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
+
+
+class C3(nn.Module):
+    # CSP Bottleneck with 3 convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(C3, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+        # self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
+
+    def forward(self, x):
+        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
+
+
+class SPP(nn.Module):
+    # Spatial pyramid pooling layer used in YOLOv3-SPP
+    def __init__(self, c1, c2, k=(5, 9, 13)):
+        super(SPP, self).__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
+        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+
+    def forward(self, x):
+        x = self.cv1(x)
+        return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
+
+
+class Focus(nn.Module):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Focus, self).__init__()
+        self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
+
+    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+        return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
+
+
+class Concat(nn.Module):
+    # Concatenate a list of tensors along dimension
+    def __init__(self, dimension=1):
+        super(Concat, self).__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        return torch.cat(x, self.d)
+
+
+class NMS(nn.Module):
+    # Non-Maximum Suppression (NMS) module
+    conf = 0.25  # confidence threshold
+    iou = 0.45  # IoU threshold
+    classes = None  # (optional list) filter by class
+
+    def __init__(self):
+        super(NMS, self).__init__()
+
+    def forward(self, x):
+        return non_max_suppression(x[0], conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)
+
+
+class autoShape(nn.Module):
+    # input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
+    img_size = 640  # inference size (pixels)
+    conf = 0.25  # NMS confidence threshold
+    iou = 0.45  # NMS IoU threshold
+    classes = None  # (optional list) filter by class
+
+    def __init__(self, model):
+        super(autoShape, self).__init__()
+        self.model = model.eval()
+
+    def autoshape(self):
+        print('autoShape already enabled, skipping... ')  # model already converted to model.autoshape()
+        return self
+
+    def forward(self, imgs, size=640, augment=False, profile=False):
+        # Inference from various sources. For height=720, width=1280, RGB images example inputs are:
+        #   filename:   imgs = 'data/samples/zidane.jpg'
+        #   URI:             = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/zidane.jpg'
+        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(720,1280,3)
+        #   PIL:             = Image.open('image.jpg')  # HWC x(720,1280,3)
+        #   numpy:           = np.zeros((720,1280,3))  # HWC
+        #   torch:           = torch.zeros(16,3,720,1280)  # BCHW
+        #   multiple:        = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images
+
+        p = next(self.model.parameters())  # for device and type
+        if isinstance(imgs, torch.Tensor):  # torch
+            return self.model(imgs.to(p.device).type_as(p), augment, profile)  # inference
+
+        # Pre-process
+        n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs])  # number of images, list of images
+        shape0, shape1 = [], []  # image and inference shapes
+        for i, im in enumerate(imgs):
+            if isinstance(im, str):  # filename or uri
+                im = Image.open(requests.get(im, stream=True).raw if im.startswith('http') else im)  # open
+            im = np.array(im)  # to numpy
+            if im.shape[0] < 5:  # image in CHW
+                im = im.transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
+            im = im[:, :, :3] if im.ndim == 3 else np.tile(im[:, :, None], 3)  # enforce 3ch input
+            s = im.shape[:2]  # HWC
+            shape0.append(s)  # image shape
+            g = (size / max(s))  # gain
+            shape1.append([y * g for y in s])
+            imgs[i] = im  # update
+        shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)]  # inference shape
+        x = [letterbox(im, new_shape=shape1, auto=False)[0] for im in imgs]  # pad
+        x = np.stack(x, 0) if n > 1 else x[0][None]  # stack
+        x = np.ascontiguousarray(x.transpose((0, 3, 1, 2)))  # BHWC to BCHW
+        x = torch.from_numpy(x).to(p.device).type_as(p) / 255.  # uint8 to fp16/32
+
+        # Inference
+        with torch.no_grad():
+            y = self.model(x, augment, profile)[0]  # forward
+        y = non_max_suppression(y, conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)  # NMS
+
+        # Post-process
+        for i in range(n):
+            scale_coords(shape1, y[i][:, :4], shape0[i])
+
+        return Detections(imgs, y, self.names)
+
+
+class Detections:
+    # detections class for YOLOv5 inference results
+    def __init__(self, imgs, pred, names=None):
+        super(Detections, self).__init__()
+        d = pred[0].device  # device
+        gn = [torch.tensor([*[im.shape[i] for i in [1, 0, 1, 0]], 1., 1.], device=d) for im in imgs]  # normalizations
+        self.imgs = imgs  # list of images as numpy arrays
+        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
+        self.names = names  # class names
+        self.xyxy = pred  # xyxy pixels
+        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
+        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
+        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
+        self.n = len(self.pred)
+
+    def display(self, pprint=False, show=False, save=False):
+        colors = color_list()
+        for i, (img, pred) in enumerate(zip(self.imgs, self.pred)):
+            str = f'Image {i + 1}/{len(self.pred)}: {img.shape[0]}x{img.shape[1]} '
+            if pred is not None:
+                for c in pred[:, -1].unique():
+                    n = (pred[:, -1] == c).sum()  # detections per class
+                    str += f'{n} {self.names[int(c)]}s, '  # add to string
+                if show or save:
+                    img = Image.fromarray(img.astype(np.uint8)) if isinstance(img, np.ndarray) else img  # from np
+                    for *box, conf, cls in pred:  # xyxy, confidence, class
+                        # str += '%s %.2f, ' % (names[int(cls)], conf)  # label
+                        ImageDraw.Draw(img).rectangle(box, width=4, outline=colors[int(cls) % 10])  # plot
+            if save:
+                f = f'results{i}.jpg'
+                str += f"saved to '{f}'"
+                img.save(f)  # save
+            if show:
+                img.show(f'Image {i}')  # show
+            if pprint:
+                print(str)
+
+    def print(self):
+        self.display(pprint=True)  # print results
+
+    def show(self):
+        self.display(show=True)  # show results
+
+    def save(self):
+        self.display(save=True)  # save results
+
+    def __len__(self):
+        return self.n
+
+    def tolist(self):
+        # return a list of Detections objects, i.e. 'for result in results.tolist():'
+        x = [Detections([self.imgs[i]], [self.pred[i]], self.names) for i in range(self.n)]
+        for d in x:
+            for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
+                setattr(d, k, getattr(d, k)[0])  # pop out of list
+        return x
+
+
+class Flatten(nn.Module):
+    # Use after nn.AdaptiveAvgPool2d(1) to remove last 2 dimensions
+    @staticmethod
+    def forward(x):
+        return x.view(x.size(0), -1)
+
+
+class Classify(nn.Module):
+    # Classification head, i.e. x(b,c1,20,20) to x(b,c2)
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Classify, self).__init__()
+        self.aap = nn.AdaptiveAvgPool2d(1)  # to x(b,c1,1,1)
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g)  # to x(b,c2,1,1)
+        self.flat = Flatten()
+
+    def forward(self, x):
+        z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1)  # cat if list
+        return self.flat(self.conv(z))  # flatten to x(b,c2)

yolov5/models/experimental.py

@@ -0,0 +1,133 @@
+# This file contains experimental modules
+
+import numpy as np
+import torch
+import torch.nn as nn
+
+from models.common import Conv, DWConv
+from utils.google_utils import attempt_download
+
+
+class CrossConv(nn.Module):
+    # Cross Convolution Downsample
+    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
+        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
+        super(CrossConv, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, (1, k), (1, s))
+        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class Sum(nn.Module):
+    # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
+    def __init__(self, n, weight=False):  # n: number of inputs
+        super(Sum, self).__init__()
+        self.weight = weight  # apply weights boolean
+        self.iter = range(n - 1)  # iter object
+        if weight:
+            self.w = nn.Parameter(-torch.arange(1., n) / 2, requires_grad=True)  # layer weights
+
+    def forward(self, x):
+        y = x[0]  # no weight
+        if self.weight:
+            w = torch.sigmoid(self.w) * 2
+            for i in self.iter:
+                y = y + x[i + 1] * w[i]
+        else:
+            for i in self.iter:
+                y = y + x[i + 1]
+        return y
+
+
+class GhostConv(nn.Module):
+    # Ghost Convolution https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
+        super(GhostConv, self).__init__()
+        c_ = c2 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, k, s, None, g, act)
+        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
+
+    def forward(self, x):
+        y = self.cv1(x)
+        return torch.cat([y, self.cv2(y)], 1)
+
+
+class GhostBottleneck(nn.Module):
+    # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k, s):
+        super(GhostBottleneck, self).__init__()
+        c_ = c2 // 2
+        self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1),  # pw
+                                  DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
+                                  GhostConv(c_, c2, 1, 1, act=False))  # pw-linear
+        self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
+                                      Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
+
+    def forward(self, x):
+        return self.conv(x) + self.shortcut(x)
+
+
+class MixConv2d(nn.Module):
+    # Mixed Depthwise Conv https://arxiv.org/abs/1907.09595
+    def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
+        super(MixConv2d, self).__init__()
+        groups = len(k)
+        if equal_ch:  # equal c_ per group
+            i = torch.linspace(0, groups - 1E-6, c2).floor()  # c2 indices
+            c_ = [(i == g).sum() for g in range(groups)]  # intermediate channels
+        else:  # equal weight.numel() per group
+            b = [c2] + [0] * groups
+            a = np.eye(groups + 1, groups, k=-1)
+            a -= np.roll(a, 1, axis=1)
+            a *= np.array(k) ** 2
+            a[0] = 1
+            c_ = np.linalg.lstsq(a, b, rcond=None)[0].round()  # solve for equal weight indices, ax = b
+
+        self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.LeakyReLU(0.1, inplace=True)
+
+    def forward(self, x):
+        return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
+
+
+class Ensemble(nn.ModuleList):
+    # Ensemble of models
+    def __init__(self):
+        super(Ensemble, self).__init__()
+
+    def forward(self, x, augment=False):
+        y = []
+        for module in self:
+            y.append(module(x, augment)[0])
+        # y = torch.stack(y).max(0)[0]  # max ensemble
+        # y = torch.cat(y, 1)  # nms ensemble
+        y = torch.stack(y).mean(0)  # mean ensemble
+        return y, None  # inference, train output
+
+
+def attempt_load(weights, map_location=None):
+    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
+    model = Ensemble()
+    for w in weights if isinstance(weights, list) else [weights]:
+        attempt_download(w)
+        model.append(torch.load(w, map_location=map_location)['model'].float().fuse().eval())  # load FP32 model
+
+    # Compatibility updates
+    for m in model.modules():
+        if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6]:
+            m.inplace = True  # pytorch 1.7.0 compatibility
+        elif type(m) is Conv:
+            m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility
+
+    if len(model) == 1:
+        return model[-1]  # return model
+    else:
+        print('Ensemble created with %s\n' % weights)
+        for k in ['names', 'stride']:
+            setattr(model, k, getattr(model[-1], k))
+        return model  # return ensemble

yolov5/models/export.py

@@ -0,0 +1,97 @@
+"""Exports a YOLOv5 *.pt model to ONNX and TorchScript formats
+
+Usage:
+    $ export PYTHONPATH="$PWD" && python models/export.py --weights ./weights/yolov5s.pt --img 640 --batch 1
+"""
+
+import argparse
+import sys
+import time
+
+sys.path.append('./')  # to run '$ python *.py' files in subdirectories
+
+import torch
+import torch.nn as nn
+
+import models
+from models.experimental import attempt_load
+from utils.activations import Hardswish, SiLU
+from utils.general import set_logging, check_img_size
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default='./yolov5s.pt', help='weights path')  # from yolov5/models/
+    parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size')  # height, width
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    opt = parser.parse_args()
+    opt.img_size *= 2 if len(opt.img_size) == 1 else 1  # expand
+    print(opt)
+    set_logging()
+    t = time.time()
+
+    # Load PyTorch model
+    model = attempt_load(opt.weights, map_location=torch.device('cpu'))  # load FP32 model
+    labels = model.names
+
+    # Checks
+    gs = int(max(model.stride))  # grid size (max stride)
+    opt.img_size = [check_img_size(x, gs) for x in opt.img_size]  # verify img_size are gs-multiples
+
+    # Input
+    img = torch.zeros(opt.batch_size, 3, *opt.img_size)  # image size(1,3,320,192) iDetection
+
+    # Update model
+    for k, m in model.named_modules():
+        m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility
+        if isinstance(m, models.common.Conv):  # assign export-friendly activations
+            if isinstance(m.act, nn.Hardswish):
+                m.act = Hardswish()
+            elif isinstance(m.act, nn.SiLU):
+                m.act = SiLU()
+        # elif isinstance(m, models.yolo.Detect):
+        #     m.forward = m.forward_export  # assign forward (optional)
+    model.model[-1].export = True  # set Detect() layer export=True
+    y = model(img)  # dry run
+
+    # TorchScript export
+    try:
+        print('\nStarting TorchScript export with torch %s...' % torch.__version__)
+        f = opt.weights.replace('.pt', '.torchscript.pt')  # filename
+        ts = torch.jit.trace(model, img)
+        ts.save(f)
+        print('TorchScript export success, saved as %s' % f)
+    except Exception as e:
+        print('TorchScript export failure: %s' % e)
+
+    # ONNX export
+    try:
+        import onnx
+
+        print('\nStarting ONNX export with onnx %s...' % onnx.__version__)
+        f = opt.weights.replace('.pt', '.onnx')  # filename
+        torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],
+                          output_names=['classes', 'boxes'] if y is None else ['output'])
+
+        # Checks
+        onnx_model = onnx.load(f)  # load onnx model
+        onnx.checker.check_model(onnx_model)  # check onnx model
+        # print(onnx.helper.printable_graph(onnx_model.graph))  # print a human readable model
+        print('ONNX export success, saved as %s' % f)
+    except Exception as e:
+        print('ONNX export failure: %s' % e)
+
+    # CoreML export
+    try:
+        import coremltools as ct
+
+        print('\nStarting CoreML export with coremltools %s...' % ct.__version__)
+        # convert model from torchscript and apply pixel scaling as per detect.py
+        model = ct.convert(ts, inputs=[ct.ImageType(name='image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
+        f = opt.weights.replace('.pt', '.mlmodel')  # filename
+        model.save(f)
+        print('CoreML export success, saved as %s' % f)
+    except Exception as e:
+        print('CoreML export failure: %s' % e)
+
+    # Finish
+    print('\nExport complete (%.2fs). Visualize with https://github.com/lutzroeder/netron.' % (time.time() - t))

yolov5/models/hub/yolov3-spp.yaml

@@ -0,0 +1,51 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3-SPP head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, SPP, [512, [5, 9, 13]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

yolov5/models/hub/yolov3-tiny.yaml

@@ -0,0 +1,41 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,14, 23,27, 37,58]  # P4/16
+  - [81,82, 135,169, 344,319]  # P5/32
+
+# YOLOv3-tiny backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [16, 3, 1]],  # 0
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 1-P1/2
+   [-1, 1, Conv, [32, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 3-P2/4
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 5-P3/8
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 7-P4/16
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 9-P5/32
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]],  # 11
+   [-1, 1, nn.MaxPool2d, [2, 1, 0]],  # 12
+  ]
+
+# YOLOv3-tiny head
+head:
+  [[-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Conv, [256, 3, 1]],  # 19 (P4/16-medium)
+
+   [[19, 15], 1, Detect, [nc, anchors]],  # Detect(P4, P5)
+  ]

yolov5/models/hub/yolov3.yaml

@@ -0,0 +1,51 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3 head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, Conv, [512, [1, 1]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

yolov5/models/hub/yolov5-fpn.yaml

@@ -0,0 +1,42 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, BottleneckCSP, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, BottleneckCSP, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 6, BottleneckCSP, [1024]],  # 9
+  ]
+
+# YOLOv5 FPN head
+head:
+  [[-1, 3, BottleneckCSP, [1024, False]],  # 10 (P5/32-large)
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 3, BottleneckCSP, [512, False]],  # 14 (P4/16-medium)
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 3, BottleneckCSP, [256, False]],  # 18 (P3/8-small)
+
+   [[18, 14, 10], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/hub/yolov5-panet.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, BottleneckCSP, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, BottleneckCSP, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, BottleneckCSP, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, BottleneckCSP, [1024, False]],  # 9
+  ]
+
+# YOLOv5 PANet head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, BottleneckCSP, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, BottleneckCSP, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/yolo.py

@@ -0,0 +1,286 @@
+import argparse
+import logging
+import math
+import sys
+from copy import deepcopy
+from pathlib import Path
+
+import torch
+import torch.nn as nn
+
+sys.path.append('./')  # to run '$ python *.py' files in subdirectories
+logger = logging.getLogger(__name__)
+
+from models.common import Conv, Bottleneck, SPP, DWConv, Focus, BottleneckCSP, C3, Concat, NMS, autoShape
+from models.experimental import MixConv2d, CrossConv
+from utils.autoanchor import check_anchor_order
+from utils.general import make_divisible, check_file, set_logging
+from utils.torch_utils import time_synchronized, fuse_conv_and_bn, model_info, scale_img, initialize_weights, \
+    select_device, copy_attr
+
+try:
+    import thop  # for FLOPS computation
+except ImportError:
+    thop = None
+
+
+class Detect(nn.Module):
+    stride = None  # strides computed during build
+    export = False  # onnx export
+
+    def __init__(self, nc=80, anchors=(), ch=()):  # detection layer
+        super(Detect, self).__init__()
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.zeros(1)] * self.nl  # init grid
+        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
+        self.register_buffer('anchors', a)  # shape(nl,na,2)
+        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+
+    def forward(self, x):
+        # x = x.copy()  # for profiling
+        z = []  # inference output
+        self.training |= self.export
+        for i in range(self.nl):
+            x[i] = self.m[i](x[i])  # conv
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
+
+                y = x[i].sigmoid()
+                y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i].to(x[i].device)) * self.stride[i]  # xy
+                y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                z.append(y.view(bs, -1, self.no))
+
+        return x if self.training else (torch.cat(z, 1), x)
+
+    @staticmethod
+    def _make_grid(nx=20, ny=20):
+        yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+        return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+
+
+class Model(nn.Module):
+    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None):  # model, input channels, number of classes
+        super(Model, self).__init__()
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
+        else:  # is *.yaml
+            import yaml  # for torch hub
+            self.yaml_file = Path(cfg).name
+            with open(cfg) as f:
+                self.yaml = yaml.load(f, Loader=yaml.FullLoader)  # model dict
+
+        # Define model
+        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
+        if nc and nc != self.yaml['nc']:
+            logger.info('Overriding model.yaml nc=%g with nc=%g' % (self.yaml['nc'], nc))
+            self.yaml['nc'] = nc  # override yaml value
+        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
+        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
+        # print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
+
+        # Build strides, anchors
+        m = self.model[-1]  # Detect()
+        if isinstance(m, Detect):
+            s = 128  # 2x min stride
+            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
+            m.anchors /= m.stride.view(-1, 1, 1)
+            check_anchor_order(m)
+            self.stride = m.stride
+            self._initialize_biases()  # only run once
+            # print('Strides: %s' % m.stride.tolist())
+
+        # Init weights, biases
+        initialize_weights(self)
+        self.info()
+        logger.info('')
+
+    def forward(self, x, augment=False, profile=False):
+        if augment:
+            img_size = x.shape[-2:]  # height, width
+            s = [1, 0.83, 0.67]  # scales
+            f = [None, 3, None]  # flips (2-ud, 3-lr)
+            y = []  # outputs
+            for si, fi in zip(s, f):
+                xi = scale_img(x.flip(fi) if fi else x, si)
+                yi = self.forward_once(xi)[0]  # forward
+                # cv2.imwrite('img%g.jpg' % s, 255 * xi[0].numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
+                yi[..., :4] /= si  # de-scale
+                if fi == 2:
+                    yi[..., 1] = img_size[0] - yi[..., 1]  # de-flip ud
+                elif fi == 3:
+                    yi[..., 0] = img_size[1] - yi[..., 0]  # de-flip lr
+                y.append(yi)
+            return torch.cat(y, 1), None  # augmented inference, train
+        else:
+            return self.forward_once(x, profile)  # single-scale inference, train
+
+    def forward_once(self, x, profile=False):
+        y, dt = [], []  # outputs
+        for m in self.model:
+            if m.f != -1:  # if not from previous layer
+                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
+
+            if profile:
+                o = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPS
+                t = time_synchronized()
+                for _ in range(10):
+                    _ = m(x)
+                dt.append((time_synchronized() - t) * 100)
+                print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
+
+            x = m(x)  # run
+            y.append(x if m.i in self.save else None)  # save output
+
+        if profile:
+            print('%.1fms total' % sum(dt))
+        return x
+
+    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
+        # https://arxiv.org/abs/1708.02002 section 3.3
+        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+        m = self.model[-1]  # Detect() module
+        for mi, s in zip(m.m, m.stride):  # from
+            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())  # cls
+            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+
+    def _print_biases(self):
+        m = self.model[-1]  # Detect() module
+        for mi in m.m:  # from
+            b = mi.bias.detach().view(m.na, -1).T  # conv.bias(255) to (3,85)
+            print(('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
+
+    # def _print_weights(self):
+    #     for m in self.model.modules():
+    #         if type(m) is Bottleneck:
+    #             print('%10.3g' % (m.w.detach().sigmoid() * 2))  # shortcut weights
+
+    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
+        print('Fusing layers... ')
+        for m in self.model.modules():
+            if type(m) is Conv and hasattr(m, 'bn'):
+                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
+                delattr(m, 'bn')  # remove batchnorm
+                m.forward = m.fuseforward  # update forward
+        self.info()
+        return self
+
+    def nms(self, mode=True):  # add or remove NMS module
+        present = type(self.model[-1]) is NMS  # last layer is NMS
+        if mode and not present:
+            print('Adding NMS... ')
+            m = NMS()  # module
+            m.f = -1  # from
+            m.i = self.model[-1].i + 1  # index
+            self.model.add_module(name='%s' % m.i, module=m)  # add
+            self.eval()
+        elif not mode and present:
+            print('Removing NMS... ')
+            self.model = self.model[:-1]  # remove
+        return self
+
+    def autoshape(self):  # add autoShape module
+        print('Adding autoShape... ')
+        m = autoShape(self)  # wrap model
+        copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=())  # copy attributes
+        return m
+
+    def info(self, verbose=False, img_size=640):  # print model information
+        model_info(self, verbose, img_size)
+
+
+def parse_model(d, ch):  # model_dict, input_channels(3)
+    logger.info('\n%3s%18s%3s%10s  %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
+    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
+    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            try:
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+            except:
+                pass
+
+        n = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in [Conv, Bottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP, C3]:
+            c1, c2 = ch[f], args[0]
+
+            # Normal
+            # if i > 0 and args[0] != no:  # channel expansion factor
+            #     ex = 1.75  # exponential (default 2.0)
+            #     e = math.log(c2 / ch[1]) / math.log(2)
+            #     c2 = int(ch[1] * ex ** e)
+            # if m != Focus:
+
+            c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
+
+            # Experimental
+            # if i > 0 and args[0] != no:  # channel expansion factor
+            #     ex = 1 + gw  # exponential (default 2.0)
+            #     ch1 = 32  # ch[1]
+            #     e = math.log(c2 / ch1) / math.log(2)  # level 1-n
+            #     c2 = int(ch1 * ex ** e)
+            # if m != Focus:
+            #     c2 = make_divisible(c2, 8) if c2 != no else c2
+
+            args = [c1, c2, *args[1:]]
+            if m in [BottleneckCSP, C3]:
+                args.insert(2, n)
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum([ch[-1 if x == -1 else x + 1] for x in f])
+        elif m is Detect:
+            args.append([ch[x + 1] for x in f])
+            if isinstance(args[1], int):  # number of anchors
+                args[1] = [list(range(args[1] * 2))] * len(f)
+        else:
+            c2 = ch[f]
+
+        m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        np = sum([x.numel() for x in m_.parameters()])  # number params
+        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
+        logger.info('%3s%18s%3s%10.0f  %-40s%-30s' % (i, f, n, np, t, args))  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        ch.append(c2)
+    return nn.Sequential(*layers), sorted(save)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    opt = parser.parse_args()
+    opt.cfg = check_file(opt.cfg)  # check file
+    set_logging()
+    device = select_device(opt.device)
+
+    # Create model
+    model = Model(opt.cfg).to(device)
+    model.train()
+
+    # Profile
+    # img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
+    # y = model(img, profile=True)
+
+    # Tensorboard
+    # from torch.utils.tensorboard import SummaryWriter
+    # tb_writer = SummaryWriter()
+    # print("Run 'tensorboard --logdir=models/runs' to view tensorboard at http://localhost:6006/")
+    # tb_writer.add_graph(model.model, img)  # add model to tensorboard
+    # tb_writer.add_image('test', img[0], dataformats='CWH')  # add model to tensorboard

yolov5/models/yolov5l.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, BottleneckCSP, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, BottleneckCSP, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, BottleneckCSP, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, BottleneckCSP, [1024, False]],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, BottleneckCSP, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, BottleneckCSP, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/yolov5m.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, BottleneckCSP, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, BottleneckCSP, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, BottleneckCSP, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, BottleneckCSP, [1024, False]],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, BottleneckCSP, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, BottleneckCSP, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/yolov5s.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, BottleneckCSP, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, BottleneckCSP, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, BottleneckCSP, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, BottleneckCSP, [1024, False]],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, BottleneckCSP, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, BottleneckCSP, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/yolov5x.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, BottleneckCSP, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, BottleneckCSP, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, BottleneckCSP, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, BottleneckCSP, [1024, False]],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, BottleneckCSP, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, BottleneckCSP, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/player.py

@@ -0,0 +1,227 @@
+import numpy as np
+import cv2
+import torch
+import colorsys
+from sklearn.cluster import KMeans
+from collections import Counter
+
+class Player:
+
+    def __init__(self,id,color=None,team=None,x=None,y=None):
+        self.id = id
+        self.x = x
+        self.y = y
+        self.team = team
+        self.color = color
+
+    def updatePosition(self, x, y):
+        self.x = x
+        self.y = y
+
+    def assignTeam(self, players):
+        if self.team is None:
+            temp_list = []
+            for key in players:
+                temp_list.append(players[key].color)
+            color_matrix = np.vstack((temp_list))
+            clt = KMeans(n_clusters=3)
+            clt.fit(color_matrix)
+            n_pixels = len(clt.labels_)
+            counter = Counter(clt.labels_)
+            perc = {}
+            for i in counter:
+                perc[i] = np.round(counter[i]/n_pixels, 2)
+            perc = dict(sorted(perc.items()))
+
+            main_colors = clt.cluster_centers_
+
+            max_value = max(perc, key=perc.get)
+            med_temp = list(sorted(perc.values()))[-2]
+            med_value = list(perc.keys())[list(perc.values()).index(med_temp)]
+            min_value = min(perc, key=perc.get)
+
+            # hsv_player = cv2.cvtColor(np.uint8([[self.color]]), cv2.COLOR_BGR2HSV)
+
+            # bgr_max = np.uint8([[main_colors[max_value]]])
+            # hsv_max = cv2.cvtColor(bgr_max, cv2.COLOR_BGR2HSV)
+
+            # bgr_med = np.uint8([[main_colors[med_value]]])
+            # hsv_med = cv2.cvtColor(bgr_med, cv2.COLOR_BGR2HSV)
+            
+            # bgr_min = np.uint8([[main_colors[min_value]]])
+            # hsv_min = cv2.cvtColor(bgr_min, cv2.COLOR_BGR2HSV)
+
+            # adjust_array = np.array([10, 10, 40])
+
+            # lower_team1 = np.subtract(hsv_max, adjust_array)
+            # upper_team1 = np.add(hsv_max, adjust_array)
+
+            # lower_team2 = np.subtract(hsv_med, adjust_array)
+            # upper_team2 = np.add(hsv_med, adjust_array)
+
+            # lower_team3 = np.subtract(hsv_min, adjust_array)
+            # upper_team3 = np.add(hsv_min, adjust_array)
+
+            # mask_team1 = cv2.inRange(hsv_player, lower_team1, upper_team1)
+            # mask_team2 = cv2.inRange(hsv_player, lower_team2, upper_team2)
+            # mask_team3 = cv2.inRange(hsv_player, lower_team3, upper_team3)
+            
+            # nonZero1 = cv2.countNonZero(mask_team1)
+            # nonZero2 = cv2.countNonZero(mask_team2)
+            # nonZero3 = cv2.countNonZero(mask_team3)
+            
+            # maxNonZero = max(nonZero1, nonZero2, nonZero3)
+            
+            # if maxNonZero == nonZero1:
+            #     self.team = 1
+            #     self.color = main_colors[max_value]
+            # elif maxNonZero == nonZero2:
+            #     self.team = 2
+            #     self.color = main_colors[med_value]
+            # else:
+            #     self.team = 3
+            #     self.color = main_colors[min_value]
+
+
+            distances = np.sqrt(np.sum((main_colors-self.color)**2,axis=1))
+
+            index_of_smallest = np.where(distances==np.amin(distances))
+            smallest_distance = main_colors[index_of_smallest]
+            if np.all(smallest_distance == main_colors[max_value]):
+                self.color = smallest_distance.flatten()
+                self.team = "Team_1"
+                # print(self.color, self.team)
+            elif np.all(smallest_distance == main_colors[med_value]):
+                self.color = smallest_distance.flatten()
+                self.team = "Team_2"
+                # print(self.color, self.team)
+            else:
+                self.color = self.color
+                self.team = "Other"
+                # print(self.color, self.team)
+
+            # print(smallest_distance)
+            # print (main_colors[max_value], main_colors[med_value], main_colors[min_value])
+
+def k_means(img):
+    clt = KMeans(n_clusters=4)
+    clt = clt.fit(img.reshape(-1, 3))
+    n_pixels = len(clt.labels_)
+    counter = Counter(clt.labels_)
+    perc = {}
+    for i in counter:
+        perc[i] = np.round(counter[i]/n_pixels, 2)
+    perc = dict(sorted(perc.items()))
+
+    return perc, clt.cluster_centers_
+
+
+def detectPlayerColor(img,x1,x2,y1,y2):
+    crop = img[y1:y2, x1:x2]
+    height, width, channels = crop.shape
+    qrt = crop[int(height/4):int(height/2), int(width/5):int(width/1.25)]
+    
+    perc, colors = k_means(qrt)
+    max_value = max(perc, key=perc.get)
+    return colors[max_value]
+
+def check_color_manual(img,x1,x2,y1,y2):
+    hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+    crop = hsv[y1:y2, x1:x2]
+
+    height, width, channels = crop.shape
+    qrt = crop[int(height/4):int(height/2), int(width/5):int(width/1.25)]
+
+    # rgb
+    team1 = np.array([37,69,234])
+    team2 = np.array([255,217,215])
+    team3 = np.array([0,0,0])
+
+    # hsv
+    lower_team1 = np.array([-5, 225, 215])
+    upper_team1 = np.array([15, 245, 295])
+
+    lower_team2 = np.array([108, 33, 215])
+    upper_team2 = np.array([128, 53, 295])
+
+    lower_team3 = np.array([144, 25, 11])
+    upper_team3 = np.array([164, 45, 91])
+
+    mask_team1 = cv2.inRange(qrt, lower_team1, upper_team1)
+    mask_team2 = cv2.inRange(qrt, lower_team2, upper_team2)
+    mask_team3 = cv2.inRange(qrt, lower_team3, upper_team3)
+
+    # out1 = cv2.bitwise_and(crop, crop, mask=mask_team1)
+    # out2 = cv2.bitwise_and(crop, crop, mask=mask_team2)
+
+    nonZero1 = cv2.countNonZero(mask_team1)
+    nonZero2 = cv2.countNonZero(mask_team2)
+    nonZero3 = cv2.countNonZero(mask_team3)
+    
+    maxNonZero = max(nonZero1, nonZero2, nonZero3)
+    
+    if maxNonZero == nonZero1:
+        team = 1
+        color = team1
+    elif maxNonZero == nonZero2:
+        team = 2
+        color = team2
+    else:
+        team = 3
+        color = team3
+
+    return (team, color)
+
+def check_color_manual2(clicks,img,x1,x2,y1,y2):
+    hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+    crop = hsv[y1:y2, x1:x2]
+
+    height, width, channels = crop.shape
+    qrt = crop[int(height/4):int(height/2), int(width/5):int(width/1.25)]
+
+    team1 = np.array(clicks[0])
+    team2 = np.array(clicks[1])
+    team3 = np.array(clicks[2])
+
+    bgr_A = np.uint8([[clicks[0]]])
+    hsv_A = cv2.cvtColor(bgr_A, cv2.COLOR_BGR2HSV)
+
+    bgr_B = np.uint8([[clicks[1]]])
+    hsv_B = cv2.cvtColor(bgr_B, cv2.COLOR_BGR2HSV)
+            
+    bgr_C = np.uint8([[clicks[2]]])
+    hsv_C = cv2.cvtColor(bgr_C, cv2.COLOR_BGR2HSV)
+
+    adjust_array = np.array([10, 10, 40])
+
+    lower_team1 = np.subtract(hsv_A, adjust_array)
+    upper_team1 = np.add(hsv_A, adjust_array)
+
+    lower_team2 = np.subtract(hsv_B, adjust_array)
+    upper_team2 = np.add(hsv_B, adjust_array)
+
+    lower_team3 = np.subtract(hsv_C, adjust_array)
+    upper_team3 = np.add(hsv_C, adjust_array)
+
+    mask_team1 = cv2.inRange(qrt, lower_team1, upper_team1)
+    mask_team2 = cv2.inRange(qrt, lower_team2, upper_team2)
+    mask_team3 = cv2.inRange(qrt, lower_team3, upper_team3)
+
+    nonZero1 = cv2.countNonZero(mask_team1)
+    nonZero2 = cv2.countNonZero(mask_team2)
+    nonZero3 = cv2.countNonZero(mask_team3)
+    
+    maxNonZero = max(nonZero1, nonZero2, nonZero3)
+    
+    if maxNonZero == nonZero1:
+        team = 1
+        color = team1
+    elif maxNonZero == nonZero2:
+        team = 2
+        color = team2
+    else:
+        team = 3
+        color = team3
+    # print (color)
+    return (team, color)
+

yolov5/requirements.txt

@@ -0,0 +1,30 @@
+# pip install -r requirements.txt
+
+# base ----------------------------------------
+Cython
+matplotlib>=3.2.2
+numpy>=1.18.5
+opencv-python>=4.1.2
+Pillow
+PyYAML>=5.3
+scipy>=1.4.1
+tensorboard>=2.2
+torch>=1.7.0
+torchvision>=0.8.1
+tqdm>=4.41.0
+
+# logging -------------------------------------
+# wandb
+
+# plotting ------------------------------------
+seaborn>=0.11.0
+pandas
+
+# export --------------------------------------
+# coremltools==4.0
+# onnx>=1.8.0
+# scikit-learn==0.19.2  # for coreml quantization
+
+# extras --------------------------------------
+thop  # FLOPS computation
+pycocotools>=2.0  # COCO mAP

yolov5/test.py

@@ -0,0 +1,334 @@
+import argparse
+import json
+import os
+from pathlib import Path
+from threading import Thread
+
+import numpy as np
+import torch
+import yaml
+from tqdm import tqdm
+
+from models.experimental import attempt_load
+from utils.datasets import create_dataloader
+from utils.general import coco80_to_coco91_class, check_dataset, check_file, check_img_size, box_iou, \
+    non_max_suppression, scale_coords, xyxy2xywh, xywh2xyxy, set_logging, increment_path
+from utils.loss import compute_loss
+from utils.metrics import ap_per_class, ConfusionMatrix
+from utils.plots import plot_images, output_to_target, plot_study_txt
+from utils.torch_utils import select_device, time_synchronized
+
+
+def test(data,
+         weights=None,
+         batch_size=32,
+         imgsz=640,
+         conf_thres=0.001,
+         iou_thres=0.6,  # for NMS
+         save_json=False,
+         single_cls=False,
+         augment=False,
+         verbose=False,
+         model=None,
+         dataloader=None,
+         save_dir=Path(''),  # for saving images
+         save_txt=False,  # for auto-labelling
+         save_hybrid=False,  # for hybrid auto-labelling
+         save_conf=False,  # save auto-label confidences
+         plots=True,
+         log_imgs=0):  # number of logged images
+
+    # Initialize/load model and set device
+    training = model is not None
+    if training:  # called by train.py
+        device = next(model.parameters()).device  # get model device
+
+    else:  # called directly
+        set_logging()
+        device = select_device(opt.device, batch_size=batch_size)
+
+        # Directories
+        save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run
+        (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+
+        # Load model
+        model = attempt_load(weights, map_location=device)  # load FP32 model
+        imgsz = check_img_size(imgsz, s=model.stride.max())  # check img_size
+
+        # Multi-GPU disabled, incompatible with .half() https://github.com/ultralytics/yolov5/issues/99
+        # if device.type != 'cpu' and torch.cuda.device_count() > 1:
+        #     model = nn.DataParallel(model)
+
+    # Half
+    half = device.type != 'cpu'  # half precision only supported on CUDA
+    if half:
+        model.half()
+
+    # Configure
+    model.eval()
+    is_coco = data.endswith('coco.yaml')  # is COCO dataset
+    with open(data) as f:
+        data = yaml.load(f, Loader=yaml.FullLoader)  # model dict
+    check_dataset(data)  # check
+    nc = 1 if single_cls else int(data['nc'])  # number of classes
+    iouv = torch.linspace(0.5, 0.95, 10).to(device)  # iou vector for mAP@0.5:0.95
+    niou = iouv.numel()
+
+    # Logging
+    log_imgs, wandb = min(log_imgs, 100), None  # ceil
+    try:
+        import wandb  # Weights & Biases
+    except ImportError:
+        log_imgs = 0
+
+    # Dataloader
+    if not training:
+        img = torch.zeros((1, 3, imgsz, imgsz), device=device)  # init img
+        _ = model(img.half() if half else img) if device.type != 'cpu' else None  # run once
+        path = data['test'] if opt.task == 'test' else data['val']  # path to val/test images
+        dataloader = create_dataloader(path, imgsz, batch_size, model.stride.max(), opt, pad=0.5, rect=True)[0]
+
+    seen = 0
+    confusion_matrix = ConfusionMatrix(nc=nc)
+    names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)}
+    coco91class = coco80_to_coco91_class()
+    s = ('%20s' + '%12s' * 6) % ('Class', 'Images', 'Targets', 'P', 'R', 'mAP@.5', 'mAP@.5:.95')
+    p, r, f1, mp, mr, map50, map, t0, t1 = 0., 0., 0., 0., 0., 0., 0., 0., 0.
+    loss = torch.zeros(3, device=device)
+    jdict, stats, ap, ap_class, wandb_images = [], [], [], [], []
+    for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
+        img = img.to(device, non_blocking=True)
+        img = img.half() if half else img.float()  # uint8 to fp16/32
+        img /= 255.0  # 0 - 255 to 0.0 - 1.0
+        targets = targets.to(device)
+        nb, _, height, width = img.shape  # batch size, channels, height, width
+
+        with torch.no_grad():
+            # Run model
+            t = time_synchronized()
+            inf_out, train_out = model(img, augment=augment)  # inference and training outputs
+            t0 += time_synchronized() - t
+
+            # Compute loss
+            if training:
+                loss += compute_loss([x.float() for x in train_out], targets, model)[1][:3]  # box, obj, cls
+
+            # Run NMS
+            targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device)  # to pixels
+            lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
+            t = time_synchronized()
+            output = non_max_suppression(inf_out, conf_thres=conf_thres, iou_thres=iou_thres, labels=lb)
+            t1 += time_synchronized() - t
+
+        # Statistics per image
+        for si, pred in enumerate(output):
+            labels = targets[targets[:, 0] == si, 1:]
+            nl = len(labels)
+            tcls = labels[:, 0].tolist() if nl else []  # target class
+            path = Path(paths[si])
+            seen += 1
+
+            if len(pred) == 0:
+                if nl:
+                    stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls))
+                continue
+
+            # Predictions
+            predn = pred.clone()
+            scale_coords(img[si].shape[1:], predn[:, :4], shapes[si][0], shapes[si][1])  # native-space pred
+
+            # Append to text file
+            if save_txt:
+                gn = torch.tensor(shapes[si][0])[[1, 0, 1, 0]]  # normalization gain whwh
+                for *xyxy, conf, cls in predn.tolist():
+                    xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+                    line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
+                    with open(save_dir / 'labels' / (path.stem + '.txt'), 'a') as f:
+                        f.write(('%g ' * len(line)).rstrip() % line + '\n')
+
+            # W&B logging
+            if plots and len(wandb_images) < log_imgs:
+                box_data = [{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
+                             "class_id": int(cls),
+                             "box_caption": "%s %.3f" % (names[cls], conf),
+                             "scores": {"class_score": conf},
+                             "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()]
+                boxes = {"predictions": {"box_data": box_data, "class_labels": names}}  # inference-space
+                wandb_images.append(wandb.Image(img[si], boxes=boxes, caption=path.name))
+
+            # Append to pycocotools JSON dictionary
+            if save_json:
+                # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
+                image_id = int(path.stem) if path.stem.isnumeric() else path.stem
+                box = xyxy2xywh(predn[:, :4])  # xywh
+                box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
+                for p, b in zip(pred.tolist(), box.tolist()):
+                    jdict.append({'image_id': image_id,
+                                  'category_id': coco91class[int(p[5])] if is_coco else int(p[5]),
+                                  'bbox': [round(x, 3) for x in b],
+                                  'score': round(p[4], 5)})
+
+            # Assign all predictions as incorrect
+            correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device)
+            if nl:
+                detected = []  # target indices
+                tcls_tensor = labels[:, 0]
+
+                # target boxes
+                tbox = xywh2xyxy(labels[:, 1:5])
+                scale_coords(img[si].shape[1:], tbox, shapes[si][0], shapes[si][1])  # native-space labels
+                if plots:
+                    confusion_matrix.process_batch(pred, torch.cat((labels[:, 0:1], tbox), 1))
+
+                # Per target class
+                for cls in torch.unique(tcls_tensor):
+                    ti = (cls == tcls_tensor).nonzero(as_tuple=False).view(-1)  # prediction indices
+                    pi = (cls == pred[:, 5]).nonzero(as_tuple=False).view(-1)  # target indices
+
+                    # Search for detections
+                    if pi.shape[0]:
+                        # Prediction to target ious
+                        ious, i = box_iou(predn[pi, :4], tbox[ti]).max(1)  # best ious, indices
+
+                        # Append detections
+                        detected_set = set()
+                        for j in (ious > iouv[0]).nonzero(as_tuple=False):
+                            d = ti[i[j]]  # detected target
+                            if d.item() not in detected_set:
+                                detected_set.add(d.item())
+                                detected.append(d)
+                                correct[pi[j]] = ious[j] > iouv  # iou_thres is 1xn
+                                if len(detected) == nl:  # all targets already located in image
+                                    break
+
+            # Append statistics (correct, conf, pcls, tcls)
+            stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls))
+
+        # Plot images
+        if plots and batch_i < 3:
+            f = save_dir / f'test_batch{batch_i}_labels.jpg'  # labels
+            Thread(target=plot_images, args=(img, targets, paths, f, names), daemon=True).start()
+            f = save_dir / f'test_batch{batch_i}_pred.jpg'  # predictions
+            Thread(target=plot_images, args=(img, output_to_target(output), paths, f, names), daemon=True).start()
+
+    # Compute statistics
+    stats = [np.concatenate(x, 0) for x in zip(*stats)]  # to numpy
+    if len(stats) and stats[0].any():
+        p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names)
+        p, r, ap50, ap = p[:, 0], r[:, 0], ap[:, 0], ap.mean(1)  # [P, R, AP@0.5, AP@0.5:0.95]
+        mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
+        nt = np.bincount(stats[3].astype(np.int64), minlength=nc)  # number of targets per class
+    else:
+        nt = torch.zeros(1)
+
+    # Print results
+    pf = '%20s' + '%12.3g' * 6  # print format
+    print(pf % ('all', seen, nt.sum(), mp, mr, map50, map))
+
+    # Print results per class
+    if verbose and nc > 1 and len(stats):
+        for i, c in enumerate(ap_class):
+            print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
+
+    # Print speeds
+    t = tuple(x / seen * 1E3 for x in (t0, t1, t0 + t1)) + (imgsz, imgsz, batch_size)  # tuple
+    if not training:
+        print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t)
+
+    # Plots
+    if plots:
+        confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
+        if wandb and wandb.run:
+            wandb.log({"Images": wandb_images})
+            wandb.log({"Validation": [wandb.Image(str(f), caption=f.name) for f in sorted(save_dir.glob('test*.jpg'))]})
+
+    # Save JSON
+    if save_json and len(jdict):
+        w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else ''  # weights
+        anno_json = '../coco/annotations/instances_val2017.json'  # annotations json
+        pred_json = str(save_dir / f"{w}_predictions.json")  # predictions json
+        print('\nEvaluating pycocotools mAP... saving %s...' % pred_json)
+        with open(pred_json, 'w') as f:
+            json.dump(jdict, f)
+
+        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
+            from pycocotools.coco import COCO
+            from pycocotools.cocoeval import COCOeval
+
+            anno = COCO(anno_json)  # init annotations api
+            pred = anno.loadRes(pred_json)  # init predictions api
+            eval = COCOeval(anno, pred, 'bbox')
+            if is_coco:
+                eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files]  # image IDs to evaluate
+            eval.evaluate()
+            eval.accumulate()
+            eval.summarize()
+            map, map50 = eval.stats[:2]  # update results (mAP@0.5:0.95, mAP@0.5)
+        except Exception as e:
+            print(f'pycocotools unable to run: {e}')
+
+    # Return results
+    if not training:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        print(f"Results saved to {save_dir}{s}")
+    model.float()  # for training
+    maps = np.zeros(nc) + map
+    for i, c in enumerate(ap_class):
+        maps[c] = ap[i]
+    return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(prog='test.py')
+    parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
+    parser.add_argument('--data', type=str, default='data/coco128.yaml', help='*.data path')
+    parser.add_argument('--batch-size', type=int, default=32, help='size of each image batch')
+    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
+    parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.6, help='IOU threshold for NMS')
+    parser.add_argument('--task', default='val', help="'val', 'test', 'study'")
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--verbose', action='store_true', help='report mAP by class')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-hybrid', action='store_true', help='save label+prediction hybrid results to *.txt')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file')
+    parser.add_argument('--project', default='runs/test', help='save to project/name')
+    parser.add_argument('--name', default='exp', help='save to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    opt = parser.parse_args()
+    opt.save_json |= opt.data.endswith('coco.yaml')
+    opt.data = check_file(opt.data)  # check file
+    print(opt)
+
+    if opt.task in ['val', 'test']:  # run normally
+        test(opt.data,
+             opt.weights,
+             opt.batch_size,
+             opt.img_size,
+             opt.conf_thres,
+             opt.iou_thres,
+             opt.save_json,
+             opt.single_cls,
+             opt.augment,
+             opt.verbose,
+             save_txt=opt.save_txt | opt.save_hybrid,
+             save_hybrid=opt.save_hybrid,
+             save_conf=opt.save_conf,
+             )
+
+    elif opt.task == 'study':  # run over a range of settings and save/plot
+        for weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
+            f = 'study_%s_%s.txt' % (Path(opt.data).stem, Path(weights).stem)  # filename to save to
+            x = list(range(320, 800, 64))  # x axis
+            y = []  # y axis
+            for i in x:  # img-size
+                print('\nRunning %s point %s...' % (f, i))
+                r, _, t = test(opt.data, weights, opt.batch_size, i, opt.conf_thres, opt.iou_thres, opt.save_json,
+                               plots=False)
+                y.append(r + t)  # results and times
+            np.savetxt(f, y, fmt='%10.4g')  # save
+        os.system('zip -r study.zip study_*.txt')
+        plot_study_txt(f, x)  # plot

yolov5/train.py

@@ -0,0 +1,595 @@
+import argparse
+import logging
+import math
+import os
+import random
+import time
+from pathlib import Path
+from threading import Thread
+from warnings import warn
+
+import numpy as np
+import torch.distributed as dist
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.optim as optim
+import torch.optim.lr_scheduler as lr_scheduler
+import torch.utils.data
+import yaml
+from torch.cuda import amp
+from torch.nn.parallel import DistributedDataParallel as DDP
+from torch.utils.tensorboard import SummaryWriter
+from tqdm import tqdm
+
+import test  # import test.py to get mAP after each epoch
+from models.experimental import attempt_load
+from models.yolo import Model
+from utils.autoanchor import check_anchors
+from utils.datasets import create_dataloader
+from utils.general import labels_to_class_weights, increment_path, labels_to_image_weights, init_seeds, \
+    fitness, strip_optimizer, get_latest_run, check_dataset, check_file, check_git_status, check_img_size, \
+    print_mutation, set_logging
+from utils.google_utils import attempt_download
+from utils.loss import compute_loss
+from utils.plots import plot_images, plot_labels, plot_results, plot_evolution
+from utils.torch_utils import ModelEMA, select_device, intersect_dicts, torch_distributed_zero_first
+
+logger = logging.getLogger(__name__)
+
+try:
+    import wandb
+except ImportError:
+    wandb = None
+    logger.info("Install Weights & Biases for experiment logging via 'pip install wandb' (recommended)")
+
+
+def train(hyp, opt, device, tb_writer=None, wandb=None):
+    logger.info(f'Hyperparameters {hyp}')
+    save_dir, epochs, batch_size, total_batch_size, weights, rank = \
+        Path(opt.save_dir), opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank
+
+    # Directories
+    wdir = save_dir / 'weights'
+    wdir.mkdir(parents=True, exist_ok=True)  # make dir
+    last = wdir / 'last.pt'
+    best = wdir / 'best.pt'
+    results_file = save_dir / 'results.txt'
+
+    # Save run settings
+    with open(save_dir / 'hyp.yaml', 'w') as f:
+        yaml.dump(hyp, f, sort_keys=False)
+    with open(save_dir / 'opt.yaml', 'w') as f:
+        yaml.dump(vars(opt), f, sort_keys=False)
+
+    # Configure
+    plots = not opt.evolve  # create plots
+    cuda = device.type != 'cpu'
+    init_seeds(2 + rank)
+    with open(opt.data) as f:
+        data_dict = yaml.load(f, Loader=yaml.FullLoader)  # data dict
+    with torch_distributed_zero_first(rank):
+        check_dataset(data_dict)  # check
+    train_path = data_dict['train']
+    test_path = data_dict['val']
+    nc = 1 if opt.single_cls else int(data_dict['nc'])  # number of classes
+    names = ['item'] if opt.single_cls and len(data_dict['names']) != 1 else data_dict['names']  # class names
+    assert len(names) == nc, '%g names found for nc=%g dataset in %s' % (len(names), nc, opt.data)  # check
+
+    # Model
+    pretrained = weights.endswith('.pt')
+    if pretrained:
+        with torch_distributed_zero_first(rank):
+            attempt_download(weights)  # download if not found locally
+        ckpt = torch.load(weights, map_location=device)  # load checkpoint
+        if hyp.get('anchors'):
+            ckpt['model'].yaml['anchors'] = round(hyp['anchors'])  # force autoanchor
+        model = Model(opt.cfg or ckpt['model'].yaml, ch=3, nc=nc).to(device)  # create
+        exclude = ['anchor'] if opt.cfg or hyp.get('anchors') else []  # exclude keys
+        state_dict = ckpt['model'].float().state_dict()  # to FP32
+        state_dict = intersect_dicts(state_dict, model.state_dict(), exclude=exclude)  # intersect
+        model.load_state_dict(state_dict, strict=False)  # load
+        logger.info('Transferred %g/%g items from %s' % (len(state_dict), len(model.state_dict()), weights))  # report
+    else:
+        model = Model(opt.cfg, ch=3, nc=nc).to(device)  # create
+
+    # Freeze
+    freeze = []  # parameter names to freeze (full or partial)
+    for k, v in model.named_parameters():
+        v.requires_grad = True  # train all layers
+        if any(x in k for x in freeze):
+            print('freezing %s' % k)
+            v.requires_grad = False
+
+    # Optimizer
+    nbs = 64  # nominal batch size
+    accumulate = max(round(nbs / total_batch_size), 1)  # accumulate loss before optimizing
+    hyp['weight_decay'] *= total_batch_size * accumulate / nbs  # scale weight_decay
+
+    pg0, pg1, pg2 = [], [], []  # optimizer parameter groups
+    for k, v in model.named_modules():
+        if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):
+            pg2.append(v.bias)  # biases
+        if isinstance(v, nn.BatchNorm2d):
+            pg0.append(v.weight)  # no decay
+        elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):
+            pg1.append(v.weight)  # apply decay
+
+    if opt.adam:
+        optimizer = optim.Adam(pg0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999))  # adjust beta1 to momentum
+    else:
+        optimizer = optim.SGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
+
+    optimizer.add_param_group({'params': pg1, 'weight_decay': hyp['weight_decay']})  # add pg1 with weight_decay
+    optimizer.add_param_group({'params': pg2})  # add pg2 (biases)
+    logger.info('Optimizer groups: %g .bias, %g conv.weight, %g other' % (len(pg2), len(pg1), len(pg0)))
+    del pg0, pg1, pg2
+
+    # Scheduler https://arxiv.org/pdf/1812.01187.pdf
+    # https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#OneCycleLR
+    lf = lambda x: ((1 + math.cos(x * math.pi / epochs)) / 2) * (1 - hyp['lrf']) + hyp['lrf']  # cosine
+    scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
+    # plot_lr_scheduler(optimizer, scheduler, epochs)
+
+    # Logging
+    if wandb and wandb.run is None:
+        opt.hyp = hyp  # add hyperparameters
+        wandb_run = wandb.init(config=opt, resume="allow",
+                               project='YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem,
+                               name=save_dir.stem,
+                               id=ckpt.get('wandb_id') if 'ckpt' in locals() else None)
+    loggers = {'wandb': wandb}  # loggers dict
+
+    # Resume
+    start_epoch, best_fitness = 0, 0.0
+    if pretrained:
+        # Optimizer
+        if ckpt['optimizer'] is not None:
+            optimizer.load_state_dict(ckpt['optimizer'])
+            best_fitness = ckpt['best_fitness']
+
+        # Results
+        if ckpt.get('training_results') is not None:
+            with open(results_file, 'w') as file:
+                file.write(ckpt['training_results'])  # write results.txt
+
+        # Epochs
+        start_epoch = ckpt['epoch'] + 1
+        if opt.resume:
+            assert start_epoch > 0, '%s training to %g epochs is finished, nothing to resume.' % (weights, epochs)
+        if epochs < start_epoch:
+            logger.info('%s has been trained for %g epochs. Fine-tuning for %g additional epochs.' %
+                        (weights, ckpt['epoch'], epochs))
+            epochs += ckpt['epoch']  # finetune additional epochs
+
+        del ckpt, state_dict
+
+    # Image sizes
+    gs = int(max(model.stride))  # grid size (max stride)
+    imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size]  # verify imgsz are gs-multiples
+
+    # DP mode
+    if cuda and rank == -1 and torch.cuda.device_count() > 1:
+        model = torch.nn.DataParallel(model)
+
+    # SyncBatchNorm
+    if opt.sync_bn and cuda and rank != -1:
+        model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
+        logger.info('Using SyncBatchNorm()')
+
+    # EMA
+    ema = ModelEMA(model) if rank in [-1, 0] else None
+
+    # DDP mode
+    if cuda and rank != -1:
+        model = DDP(model, device_ids=[opt.local_rank], output_device=opt.local_rank)
+
+    # Trainloader
+    dataloader, dataset = create_dataloader(train_path, imgsz, batch_size, gs, opt,
+                                            hyp=hyp, augment=True, cache=opt.cache_images, rect=opt.rect, rank=rank,
+                                            world_size=opt.world_size, workers=opt.workers,
+                                            image_weights=opt.image_weights)
+    mlc = np.concatenate(dataset.labels, 0)[:, 0].max()  # max label class
+    nb = len(dataloader)  # number of batches
+    assert mlc < nc, 'Label class %g exceeds nc=%g in %s. Possible class labels are 0-%g' % (mlc, nc, opt.data, nc - 1)
+
+    # Process 0
+    if rank in [-1, 0]:
+        ema.updates = start_epoch * nb // accumulate  # set EMA updates
+        testloader = create_dataloader(test_path, imgsz_test, total_batch_size, gs, opt,  # testloader
+                                       hyp=hyp, cache=opt.cache_images and not opt.notest, rect=True,
+                                       rank=-1, world_size=opt.world_size, workers=opt.workers, pad=0.5)[0]
+
+        if not opt.resume:
+            labels = np.concatenate(dataset.labels, 0)
+            c = torch.tensor(labels[:, 0])  # classes
+            # cf = torch.bincount(c.long(), minlength=nc) + 1.  # frequency
+            # model._initialize_biases(cf.to(device))
+            if plots:
+                plot_labels(labels, save_dir, loggers)
+                if tb_writer:
+                    tb_writer.add_histogram('classes', c, 0)
+
+            # Anchors
+            if not opt.noautoanchor:
+                check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)
+
+    # Model parameters
+    hyp['cls'] *= nc / 80.  # scale coco-tuned hyp['cls'] to current dataset
+    model.nc = nc  # attach number of classes to model
+    model.hyp = hyp  # attach hyperparameters to model
+    model.gr = 1.0  # iou loss ratio (obj_loss = 1.0 or iou)
+    model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc  # attach class weights
+    model.names = names
+
+    # Start training
+    t0 = time.time()
+    nw = max(round(hyp['warmup_epochs'] * nb), 1000)  # number of warmup iterations, max(3 epochs, 1k iterations)
+    # nw = min(nw, (epochs - start_epoch) / 2 * nb)  # limit warmup to < 1/2 of training
+    maps = np.zeros(nc)  # mAP per class
+    results = (0, 0, 0, 0, 0, 0, 0)  # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
+    scheduler.last_epoch = start_epoch - 1  # do not move
+    scaler = amp.GradScaler(enabled=cuda)
+    logger.info('Image sizes %g train, %g test\n'
+                'Using %g dataloader workers\nLogging results to %s\n'
+                'Starting training for %g epochs...' % (imgsz, imgsz_test, dataloader.num_workers, save_dir, epochs))
+    for epoch in range(start_epoch, epochs):  # epoch ------------------------------------------------------------------
+        model.train()
+
+        # Update image weights (optional)
+        if opt.image_weights:
+            # Generate indices
+            if rank in [-1, 0]:
+                cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc  # class weights
+                iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw)  # image weights
+                dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n)  # rand weighted idx
+            # Broadcast if DDP
+            if rank != -1:
+                indices = (torch.tensor(dataset.indices) if rank == 0 else torch.zeros(dataset.n)).int()
+                dist.broadcast(indices, 0)
+                if rank != 0:
+                    dataset.indices = indices.cpu().numpy()
+
+        # Update mosaic border
+        # b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
+        # dataset.mosaic_border = [b - imgsz, -b]  # height, width borders
+
+        mloss = torch.zeros(4, device=device)  # mean losses
+        if rank != -1:
+            dataloader.sampler.set_epoch(epoch)
+        pbar = enumerate(dataloader)
+        logger.info(('\n' + '%10s' * 8) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'total', 'targets', 'img_size'))
+        if rank in [-1, 0]:
+            pbar = tqdm(pbar, total=nb)  # progress bar
+        optimizer.zero_grad()
+        for i, (imgs, targets, paths, _) in pbar:  # batch -------------------------------------------------------------
+            ni = i + nb * epoch  # number integrated batches (since train start)
+            imgs = imgs.to(device, non_blocking=True).float() / 255.0  # uint8 to float32, 0-255 to 0.0-1.0
+
+            # Warmup
+            if ni <= nw:
+                xi = [0, nw]  # x interp
+                # model.gr = np.interp(ni, xi, [0.0, 1.0])  # iou loss ratio (obj_loss = 1.0 or iou)
+                accumulate = max(1, np.interp(ni, xi, [1, nbs / total_batch_size]).round())
+                for j, x in enumerate(optimizer.param_groups):
+                    # bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
+                    x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
+                    if 'momentum' in x:
+                        x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
+
+            # Multi-scale
+            if opt.multi_scale:
+                sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs  # size
+                sf = sz / max(imgs.shape[2:])  # scale factor
+                if sf != 1:
+                    ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]]  # new shape (stretched to gs-multiple)
+                    imgs = F.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
+
+            # Forward
+            with amp.autocast(enabled=cuda):
+                pred = model(imgs)  # forward
+                loss, loss_items = compute_loss(pred, targets.to(device), model)  # loss scaled by batch_size
+                if rank != -1:
+                    loss *= opt.world_size  # gradient averaged between devices in DDP mode
+
+            # Backward
+            scaler.scale(loss).backward()
+
+            # Optimize
+            if ni % accumulate == 0:
+                scaler.step(optimizer)  # optimizer.step
+                scaler.update()
+                optimizer.zero_grad()
+                if ema:
+                    ema.update(model)
+
+            # Print
+            if rank in [-1, 0]:
+                mloss = (mloss * i + loss_items) / (i + 1)  # update mean losses
+                mem = '%.3gG' % (torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0)  # (GB)
+                s = ('%10s' * 2 + '%10.4g' * 6) % (
+                    '%g/%g' % (epoch, epochs - 1), mem, *mloss, targets.shape[0], imgs.shape[-1])
+                pbar.set_description(s)
+
+                # Plot
+                if plots and ni < 3:
+                    f = save_dir / f'train_batch{ni}.jpg'  # filename
+                    Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start()
+                    # if tb_writer:
+                    #     tb_writer.add_image(f, result, dataformats='HWC', global_step=epoch)
+                    #     tb_writer.add_graph(model, imgs)  # add model to tensorboard
+                elif plots and ni == 3 and wandb:
+                    wandb.log({"Mosaics": [wandb.Image(str(x), caption=x.name) for x in save_dir.glob('train*.jpg')]})
+
+            # end batch ------------------------------------------------------------------------------------------------
+        # end epoch ----------------------------------------------------------------------------------------------------
+
+        # Scheduler
+        lr = [x['lr'] for x in optimizer.param_groups]  # for tensorboard
+        scheduler.step()
+
+        # DDP process 0 or single-GPU
+        if rank in [-1, 0]:
+            # mAP
+            if ema:
+                ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'gr', 'names', 'stride', 'class_weights'])
+            final_epoch = epoch + 1 == epochs
+            if not opt.notest or final_epoch:  # Calculate mAP
+                results, maps, times = test.test(opt.data,
+                                                 batch_size=total_batch_size,
+                                                 imgsz=imgsz_test,
+                                                 model=ema.ema,
+                                                 single_cls=opt.single_cls,
+                                                 dataloader=testloader,
+                                                 save_dir=save_dir,
+                                                 plots=plots and final_epoch,
+                                                 log_imgs=opt.log_imgs if wandb else 0)
+
+            # Write
+            with open(results_file, 'a') as f:
+                f.write(s + '%10.4g' * 7 % results + '\n')  # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
+            if len(opt.name) and opt.bucket:
+                os.system('gsutil cp %s gs://%s/results/results%s.txt' % (results_file, opt.bucket, opt.name))
+
+            # Log
+            tags = ['train/box_loss', 'train/obj_loss', 'train/cls_loss',  # train loss
+                    'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95',
+                    'val/box_loss', 'val/obj_loss', 'val/cls_loss',  # val loss
+                    'x/lr0', 'x/lr1', 'x/lr2']  # params
+            for x, tag in zip(list(mloss[:-1]) + list(results) + lr, tags):
+                if tb_writer:
+                    tb_writer.add_scalar(tag, x, epoch)  # tensorboard
+                if wandb:
+                    wandb.log({tag: x})  # W&B
+
+            # Update best mAP
+            fi = fitness(np.array(results).reshape(1, -1))  # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
+            if fi > best_fitness:
+                best_fitness = fi
+
+            # Save model
+            save = (not opt.nosave) or (final_epoch and not opt.evolve)
+            if save:
+                with open(results_file, 'r') as f:  # create checkpoint
+                    ckpt = {'epoch': epoch,
+                            'best_fitness': best_fitness,
+                            'training_results': f.read(),
+                            'model': ema.ema,
+                            'optimizer': None if final_epoch else optimizer.state_dict(),
+                            'wandb_id': wandb_run.id if wandb else None}
+
+                # Save last, best and delete
+                torch.save(ckpt, last)
+                if best_fitness == fi:
+                    torch.save(ckpt, best)
+                del ckpt
+        # end epoch ----------------------------------------------------------------------------------------------------
+    # end training
+
+    if rank in [-1, 0]:
+        # Strip optimizers
+        final = best if best.exists() else last  # final model
+        for f in [last, best]:
+            if f.exists():
+                strip_optimizer(f)  # strip optimizers
+        if opt.bucket:
+            os.system(f'gsutil cp {final} gs://{opt.bucket}/weights')  # upload
+
+        # Plots
+        if plots:
+            plot_results(save_dir=save_dir)  # save as results.png
+            if wandb:
+                files = ['results.png', 'precision_recall_curve.png', 'confusion_matrix.png']
+                wandb.log({"Results": [wandb.Image(str(save_dir / f), caption=f) for f in files
+                                       if (save_dir / f).exists()]})
+                if opt.log_artifacts:
+                    wandb.log_artifact(artifact_or_path=str(final), type='model', name=save_dir.stem)
+
+        # Test best.pt
+        logger.info('%g epochs completed in %.3f hours.\n' % (epoch - start_epoch + 1, (time.time() - t0) / 3600))
+        if opt.data.endswith('coco.yaml') and nc == 80:  # if COCO
+            for conf, iou, save_json in ([0.25, 0.45, False], [0.001, 0.65, True]):  # speed, mAP tests
+                results, _, _ = test.test(opt.data,
+                                          batch_size=total_batch_size,
+                                          imgsz=imgsz_test,
+                                          conf_thres=conf,
+                                          iou_thres=iou,
+                                          model=attempt_load(final, device).half(),
+                                          single_cls=opt.single_cls,
+                                          dataloader=testloader,
+                                          save_dir=save_dir,
+                                          save_json=save_json,
+                                          plots=False)
+
+    else:
+        dist.destroy_process_group()
+
+    wandb.run.finish() if wandb and wandb.run else None
+    torch.cuda.empty_cache()
+    return results
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default='yolov5s.pt', help='initial weights path')
+    parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
+    parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path')
+    parser.add_argument('--hyp', type=str, default='data/hyp.scratch.yaml', help='hyperparameters path')
+    parser.add_argument('--epochs', type=int, default=300)
+    parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs')
+    parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='[train, test] image sizes')
+    parser.add_argument('--rect', action='store_true', help='rectangular training')
+    parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
+    parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
+    parser.add_argument('--notest', action='store_true', help='only test final epoch')
+    parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
+    parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters')
+    parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
+    parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
+    parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
+    parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
+    parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
+    parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
+    parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
+    parser.add_argument('--log-imgs', type=int, default=16, help='number of images for W&B logging, max 100')
+    parser.add_argument('--log-artifacts', action='store_true', help='log artifacts, i.e. final trained model')
+    parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
+    parser.add_argument('--project', default='runs/train', help='save to project/name')
+    parser.add_argument('--name', default='exp', help='save to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    opt = parser.parse_args()
+
+    # Set DDP variables
+    opt.total_batch_size = opt.batch_size
+    opt.world_size = int(os.environ['WORLD_SIZE']) if 'WORLD_SIZE' in os.environ else 1
+    opt.global_rank = int(os.environ['RANK']) if 'RANK' in os.environ else -1
+    set_logging(opt.global_rank)
+    if opt.global_rank in [-1, 0]:
+        check_git_status()
+
+    # Resume
+    if opt.resume:  # resume an interrupted run
+        ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run()  # specified or most recent path
+        assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
+        apriori = opt.global_rank, opt.local_rank
+        with open(Path(ckpt).parent.parent / 'opt.yaml') as f:
+            opt = argparse.Namespace(**yaml.load(f, Loader=yaml.FullLoader))  # replace
+        opt.cfg, opt.weights, opt.resume, opt.global_rank, opt.local_rank = '', ckpt, True, *apriori  # reinstate
+        logger.info('Resuming training from %s' % ckpt)
+    else:
+        # opt.hyp = opt.hyp or ('hyp.finetune.yaml' if opt.weights else 'hyp.scratch.yaml')
+        opt.data, opt.cfg, opt.hyp = check_file(opt.data), check_file(opt.cfg), check_file(opt.hyp)  # check files
+        assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
+        opt.img_size.extend([opt.img_size[-1]] * (2 - len(opt.img_size)))  # extend to 2 sizes (train, test)
+        opt.name = 'evolve' if opt.evolve else opt.name
+        opt.save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok | opt.evolve)  # increment run
+
+    # DDP mode
+    device = select_device(opt.device, batch_size=opt.batch_size)
+    if opt.local_rank != -1:
+        assert torch.cuda.device_count() > opt.local_rank
+        torch.cuda.set_device(opt.local_rank)
+        device = torch.device('cuda', opt.local_rank)
+        dist.init_process_group(backend='nccl', init_method='env://')  # distributed backend
+        assert opt.batch_size % opt.world_size == 0, '--batch-size must be multiple of CUDA device count'
+        opt.batch_size = opt.total_batch_size // opt.world_size
+
+    # Hyperparameters
+    with open(opt.hyp) as f:
+        hyp = yaml.load(f, Loader=yaml.FullLoader)  # load hyps
+        if 'box' not in hyp:
+            warn('Compatibility: %s missing "box" which was renamed from "giou" in %s' %
+                 (opt.hyp, 'https://github.com/ultralytics/yolov5/pull/1120'))
+            hyp['box'] = hyp.pop('giou')
+
+    # Train
+    logger.info(opt)
+    if not opt.evolve:
+        tb_writer = None  # init loggers
+        if opt.global_rank in [-1, 0]:
+            logger.info(f'Start Tensorboard with "tensorboard --logdir {opt.project}", view at http://localhost:6006/')
+            tb_writer = SummaryWriter(opt.save_dir)  # Tensorboard
+        train(hyp, opt, device, tb_writer, wandb)
+
+    # Evolve hyperparameters (optional)
+    else:
+        # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
+        meta = {'lr0': (1, 1e-5, 1e-1),  # initial learning rate (SGD=1E-2, Adam=1E-3)
+                'lrf': (1, 0.01, 1.0),  # final OneCycleLR learning rate (lr0 * lrf)
+                'momentum': (0.3, 0.6, 0.98),  # SGD momentum/Adam beta1
+                'weight_decay': (1, 0.0, 0.001),  # optimizer weight decay
+                'warmup_epochs': (1, 0.0, 5.0),  # warmup epochs (fractions ok)
+                'warmup_momentum': (1, 0.0, 0.95),  # warmup initial momentum
+                'warmup_bias_lr': (1, 0.0, 0.2),  # warmup initial bias lr
+                'box': (1, 0.02, 0.2),  # box loss gain
+                'cls': (1, 0.2, 4.0),  # cls loss gain
+                'cls_pw': (1, 0.5, 2.0),  # cls BCELoss positive_weight
+                'obj': (1, 0.2, 4.0),  # obj loss gain (scale with pixels)
+                'obj_pw': (1, 0.5, 2.0),  # obj BCELoss positive_weight
+                'iou_t': (0, 0.1, 0.7),  # IoU training threshold
+                'anchor_t': (1, 2.0, 8.0),  # anchor-multiple threshold
+                'anchors': (2, 2.0, 10.0),  # anchors per output grid (0 to ignore)
+                'fl_gamma': (0, 0.0, 2.0),  # focal loss gamma (efficientDet default gamma=1.5)
+                'hsv_h': (1, 0.0, 0.1),  # image HSV-Hue augmentation (fraction)
+                'hsv_s': (1, 0.0, 0.9),  # image HSV-Saturation augmentation (fraction)
+                'hsv_v': (1, 0.0, 0.9),  # image HSV-Value augmentation (fraction)
+                'degrees': (1, 0.0, 45.0),  # image rotation (+/- deg)
+                'translate': (1, 0.0, 0.9),  # image translation (+/- fraction)
+                'scale': (1, 0.0, 0.9),  # image scale (+/- gain)
+                'shear': (1, 0.0, 10.0),  # image shear (+/- deg)
+                'perspective': (0, 0.0, 0.001),  # image perspective (+/- fraction), range 0-0.001
+                'flipud': (1, 0.0, 1.0),  # image flip up-down (probability)
+                'fliplr': (0, 0.0, 1.0),  # image flip left-right (probability)
+                'mosaic': (1, 0.0, 1.0),  # image mixup (probability)
+                'mixup': (1, 0.0, 1.0)}  # image mixup (probability)
+
+        assert opt.local_rank == -1, 'DDP mode not implemented for --evolve'
+        opt.notest, opt.nosave = True, True  # only test/save final epoch
+        # ei = [isinstance(x, (int, float)) for x in hyp.values()]  # evolvable indices
+        yaml_file = Path(opt.save_dir) / 'hyp_evolved.yaml'  # save best result here
+        if opt.bucket:
+            os.system('gsutil cp gs://%s/evolve.txt .' % opt.bucket)  # download evolve.txt if exists
+
+        for _ in range(300):  # generations to evolve
+            if Path('evolve.txt').exists():  # if evolve.txt exists: select best hyps and mutate
+                # Select parent(s)
+                parent = 'single'  # parent selection method: 'single' or 'weighted'
+                x = np.loadtxt('evolve.txt', ndmin=2)
+                n = min(5, len(x))  # number of previous results to consider
+                x = x[np.argsort(-fitness(x))][:n]  # top n mutations
+                w = fitness(x) - fitness(x).min()  # weights
+                if parent == 'single' or len(x) == 1:
+                    # x = x[random.randint(0, n - 1)]  # random selection
+                    x = x[random.choices(range(n), weights=w)[0]]  # weighted selection
+                elif parent == 'weighted':
+                    x = (x * w.reshape(n, 1)).sum(0) / w.sum()  # weighted combination
+
+                # Mutate
+                mp, s = 0.8, 0.2  # mutation probability, sigma
+                npr = np.random
+                npr.seed(int(time.time()))
+                g = np.array([x[0] for x in meta.values()])  # gains 0-1
+                ng = len(meta)
+                v = np.ones(ng)
+                while all(v == 1):  # mutate until a change occurs (prevent duplicates)
+                    v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
+                for i, k in enumerate(hyp.keys()):  # plt.hist(v.ravel(), 300)
+                    hyp[k] = float(x[i + 7] * v[i])  # mutate
+
+            # Constrain to limits
+            for k, v in meta.items():
+                hyp[k] = max(hyp[k], v[1])  # lower limit
+                hyp[k] = min(hyp[k], v[2])  # upper limit
+                hyp[k] = round(hyp[k], 5)  # significant digits
+
+            # Train mutation
+            results = train(hyp.copy(), opt, device, wandb=wandb)
+
+            # Write mutation results
+            print_mutation(hyp.copy(), results, yaml_file, opt.bucket)
+
+        # Plot results
+        plot_evolution(yaml_file)
+        print(f'Hyperparameter evolution complete. Best results saved as: {yaml_file}\n'
+              f'Command to train a new model with these hyperparameters: $ python train.py --hyp {yaml_file}')

yolov5/utils/activations.py

@@ -0,0 +1,72 @@
+# Activation functions
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+# SiLU https://arxiv.org/pdf/1905.02244.pdf ----------------------------------------------------------------------------
+class SiLU(nn.Module):  # export-friendly version of nn.SiLU()
+    @staticmethod
+    def forward(x):
+        return x * torch.sigmoid(x)
+
+
+class Hardswish(nn.Module):  # export-friendly version of nn.Hardswish()
+    @staticmethod
+    def forward(x):
+        # return x * F.hardsigmoid(x)  # for torchscript and CoreML
+        return x * F.hardtanh(x + 3, 0., 6.) / 6.  # for torchscript, CoreML and ONNX
+
+
+class MemoryEfficientSwish(nn.Module):
+    class F(torch.autograd.Function):
+        @staticmethod
+        def forward(ctx, x):
+            ctx.save_for_backward(x)
+            return x * torch.sigmoid(x)
+
+        @staticmethod
+        def backward(ctx, grad_output):
+            x = ctx.saved_tensors[0]
+            sx = torch.sigmoid(x)
+            return grad_output * (sx * (1 + x * (1 - sx)))
+
+    def forward(self, x):
+        return self.F.apply(x)
+
+
+# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
+class Mish(nn.Module):
+    @staticmethod
+    def forward(x):
+        return x * F.softplus(x).tanh()
+
+
+class MemoryEfficientMish(nn.Module):
+    class F(torch.autograd.Function):
+        @staticmethod
+        def forward(ctx, x):
+            ctx.save_for_backward(x)
+            return x.mul(torch.tanh(F.softplus(x)))  # x * tanh(ln(1 + exp(x)))
+
+        @staticmethod
+        def backward(ctx, grad_output):
+            x = ctx.saved_tensors[0]
+            sx = torch.sigmoid(x)
+            fx = F.softplus(x).tanh()
+            return grad_output * (fx + x * sx * (1 - fx * fx))
+
+    def forward(self, x):
+        return self.F.apply(x)
+
+
+# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
+class FReLU(nn.Module):
+    def __init__(self, c1, k=3):  # ch_in, kernel
+        super().__init__()
+        self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
+        self.bn = nn.BatchNorm2d(c1)
+
+    def forward(self, x):
+        return torch.max(x, self.bn(self.conv(x)))

yolov5/utils/autoanchor.py

@@ -0,0 +1,151 @@
+# Auto-anchor utils
+
+import numpy as np
+import torch
+import yaml
+from scipy.cluster.vq import kmeans
+from tqdm import tqdm
+
+
+def check_anchor_order(m):
+    # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary
+    a = m.anchor_grid.prod(-1).view(-1)  # anchor area
+    da = a[-1] - a[0]  # delta a
+    ds = m.stride[-1] - m.stride[0]  # delta s
+    if da.sign() != ds.sign():  # same order
+        print('Reversing anchor order')
+        m.anchors[:] = m.anchors.flip(0)
+        m.anchor_grid[:] = m.anchor_grid.flip(0)
+
+
+def check_anchors(dataset, model, thr=4.0, imgsz=640):
+    # Check anchor fit to data, recompute if necessary
+    print('\nAnalyzing anchors... ', end='')
+    m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1]  # Detect()
+    shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+    scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1))  # augment scale
+    wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float()  # wh
+
+    def metric(k):  # compute metric
+        r = wh[:, None] / k[None]
+        x = torch.min(r, 1. / r).min(2)[0]  # ratio metric
+        best = x.max(1)[0]  # best_x
+        aat = (x > 1. / thr).float().sum(1).mean()  # anchors above threshold
+        bpr = (best > 1. / thr).float().mean()  # best possible recall
+        return bpr, aat
+
+    bpr, aat = metric(m.anchor_grid.clone().cpu().view(-1, 2))
+    print('anchors/target = %.2f, Best Possible Recall (BPR) = %.4f' % (aat, bpr), end='')
+    if bpr < 0.98:  # threshold to recompute
+        print('. Attempting to improve anchors, please wait...')
+        na = m.anchor_grid.numel() // 2  # number of anchors
+        new_anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
+        new_bpr = metric(new_anchors.reshape(-1, 2))[0]
+        if new_bpr > bpr:  # replace anchors
+            new_anchors = torch.tensor(new_anchors, device=m.anchors.device).type_as(m.anchors)
+            m.anchor_grid[:] = new_anchors.clone().view_as(m.anchor_grid)  # for inference
+            m.anchors[:] = new_anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1)  # loss
+            check_anchor_order(m)
+            print('New anchors saved to model. Update model *.yaml to use these anchors in the future.')
+        else:
+            print('Original anchors better than new anchors. Proceeding with original anchors.')
+    print('')  # newline
+
+
+def kmean_anchors(path='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
+    """ Creates kmeans-evolved anchors from training dataset
+
+        Arguments:
+            path: path to dataset *.yaml, or a loaded dataset
+            n: number of anchors
+            img_size: image size used for training
+            thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
+            gen: generations to evolve anchors using genetic algorithm
+            verbose: print all results
+
+        Return:
+            k: kmeans evolved anchors
+
+        Usage:
+            from utils.autoanchor import *; _ = kmean_anchors()
+    """
+    thr = 1. / thr
+
+    def metric(k, wh):  # compute metrics
+        r = wh[:, None] / k[None]
+        x = torch.min(r, 1. / r).min(2)[0]  # ratio metric
+        # x = wh_iou(wh, torch.tensor(k))  # iou metric
+        return x, x.max(1)[0]  # x, best_x
+
+    def anchor_fitness(k):  # mutation fitness
+        _, best = metric(torch.tensor(k, dtype=torch.float32), wh)
+        return (best * (best > thr).float()).mean()  # fitness
+
+    def print_results(k):
+        k = k[np.argsort(k.prod(1))]  # sort small to large
+        x, best = metric(k, wh0)
+        bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n  # best possible recall, anch > thr
+        print('thr=%.2f: %.4f best possible recall, %.2f anchors past thr' % (thr, bpr, aat))
+        print('n=%g, img_size=%s, metric_all=%.3f/%.3f-mean/best, past_thr=%.3f-mean: ' %
+              (n, img_size, x.mean(), best.mean(), x[x > thr].mean()), end='')
+        for i, x in enumerate(k):
+            print('%i,%i' % (round(x[0]), round(x[1])), end=',  ' if i < len(k) - 1 else '\n')  # use in *.cfg
+        return k
+
+    if isinstance(path, str):  # *.yaml file
+        with open(path) as f:
+            data_dict = yaml.load(f, Loader=yaml.FullLoader)  # model dict
+        from utils.datasets import LoadImagesAndLabels
+        dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
+    else:
+        dataset = path  # dataset
+
+    # Get label wh
+    shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+    wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)])  # wh
+
+    # Filter
+    i = (wh0 < 3.0).any(1).sum()
+    if i:
+        print('WARNING: Extremely small objects found. '
+              '%g of %g labels are < 3 pixels in width or height.' % (i, len(wh0)))
+    wh = wh0[(wh0 >= 2.0).any(1)]  # filter > 2 pixels
+
+    # Kmeans calculation
+    print('Running kmeans for %g anchors on %g points...' % (n, len(wh)))
+    s = wh.std(0)  # sigmas for whitening
+    k, dist = kmeans(wh / s, n, iter=30)  # points, mean distance
+    k *= s
+    wh = torch.tensor(wh, dtype=torch.float32)  # filtered
+    wh0 = torch.tensor(wh0, dtype=torch.float32)  # unfiltered
+    k = print_results(k)
+
+    # Plot
+    # k, d = [None] * 20, [None] * 20
+    # for i in tqdm(range(1, 21)):
+    #     k[i-1], d[i-1] = kmeans(wh / s, i)  # points, mean distance
+    # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
+    # ax = ax.ravel()
+    # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
+    # fig, ax = plt.subplots(1, 2, figsize=(14, 7))  # plot wh
+    # ax[0].hist(wh[wh[:, 0]<100, 0],400)
+    # ax[1].hist(wh[wh[:, 1]<100, 1],400)
+    # fig.savefig('wh.png', dpi=200)
+
+    # Evolve
+    npr = np.random
+    f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1  # fitness, generations, mutation prob, sigma
+    pbar = tqdm(range(gen), desc='Evolving anchors with Genetic Algorithm')  # progress bar
+    for _ in pbar:
+        v = np.ones(sh)
+        while (v == 1).all():  # mutate until a change occurs (prevent duplicates)
+            v = ((npr.random(sh) < mp) * npr.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
+        kg = (k.copy() * v).clip(min=2.0)
+        fg = anchor_fitness(kg)
+        if fg > f:
+            f, k = fg, kg.copy()
+            pbar.desc = 'Evolving anchors with Genetic Algorithm: fitness = %.4f' % f
+            if verbose:
+                print_results(k)
+
+    return print_results(k)

yolov5/utils/datasets.py

@@ -0,0 +1,934 @@
+# Dataset utils and dataloaders
+
+import glob
+import logging
+import math
+import os
+import random
+import shutil
+import time
+from itertools import repeat
+from multiprocessing.pool import ThreadPool
+from pathlib import Path
+from threading import Thread
+
+import cv2
+import numpy as np
+import torch
+from PIL import Image, ExifTags
+from torch.utils.data import Dataset
+from tqdm import tqdm
+
+from utils.general import xyxy2xywh, xywh2xyxy, clean_str
+from utils.torch_utils import torch_distributed_zero_first
+
+# Parameters
+help_url = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
+img_formats = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng']  # acceptable image suffixes
+vid_formats = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv']  # acceptable video suffixes
+logger = logging.getLogger(__name__)
+
+# Get orientation exif tag
+for orientation in ExifTags.TAGS.keys():
+    if ExifTags.TAGS[orientation] == 'Orientation':
+        break
+
+
+def get_hash(files):
+    # Returns a single hash value of a list of files
+    return sum(os.path.getsize(f) for f in files if os.path.isfile(f))
+
+
+def exif_size(img):
+    # Returns exif-corrected PIL size
+    s = img.size  # (width, height)
+    try:
+        rotation = dict(img._getexif().items())[orientation]
+        if rotation == 6:  # rotation 270
+            s = (s[1], s[0])
+        elif rotation == 8:  # rotation 90
+            s = (s[1], s[0])
+    except:
+        pass
+
+    return s
+
+
+def create_dataloader(path, imgsz, batch_size, stride, opt, hyp=None, augment=False, cache=False, pad=0.0, rect=False,
+                      rank=-1, world_size=1, workers=8, image_weights=False):
+    # Make sure only the first process in DDP process the dataset first, and the following others can use the cache
+    with torch_distributed_zero_first(rank):
+        dataset = LoadImagesAndLabels(path, imgsz, batch_size,
+                                      augment=augment,  # augment images
+                                      hyp=hyp,  # augmentation hyperparameters
+                                      rect=rect,  # rectangular training
+                                      cache_images=cache,
+                                      single_cls=opt.single_cls,
+                                      stride=int(stride),
+                                      pad=pad,
+                                      rank=rank,
+                                      image_weights=image_weights)
+
+    batch_size = min(batch_size, len(dataset))
+    nw = min([os.cpu_count() // world_size, batch_size if batch_size > 1 else 0, workers])  # number of workers
+    sampler = torch.utils.data.distributed.DistributedSampler(dataset) if rank != -1 else None
+    loader = torch.utils.data.DataLoader if image_weights else InfiniteDataLoader
+    # Use torch.utils.data.DataLoader() if dataset.properties will update during training else InfiniteDataLoader()
+    dataloader = loader(dataset,
+                        batch_size=batch_size,
+                        num_workers=nw,
+                        sampler=sampler,
+                        pin_memory=True,
+                        collate_fn=LoadImagesAndLabels.collate_fn)
+    return dataloader, dataset
+
+
+class InfiniteDataLoader(torch.utils.data.dataloader.DataLoader):
+    """ Dataloader that reuses workers
+
+    Uses same syntax as vanilla DataLoader
+    """
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler))
+        self.iterator = super().__iter__()
+
+    def __len__(self):
+        return len(self.batch_sampler.sampler)
+
+    def __iter__(self):
+        for i in range(len(self)):
+            yield next(self.iterator)
+
+
+class _RepeatSampler(object):
+    """ Sampler that repeats forever
+
+    Args:
+        sampler (Sampler)
+    """
+
+    def __init__(self, sampler):
+        self.sampler = sampler
+
+    def __iter__(self):
+        while True:
+            yield from iter(self.sampler)
+
+
+class LoadImages:  # for inference
+    def __init__(self, path, img_size=640):
+        p = str(Path(path))  # os-agnostic
+        p = os.path.abspath(p)  # absolute path
+        if '*' in p:
+            files = sorted(glob.glob(p, recursive=True))  # glob
+        elif os.path.isdir(p):
+            files = sorted(glob.glob(os.path.join(p, '*.*')))  # dir
+        elif os.path.isfile(p):
+            files = [p]  # files
+        else:
+            raise Exception('ERROR: %s does not exist' % p)
+
+        images = [x for x in files if x.split('.')[-1].lower() in img_formats]
+        videos = [x for x in files if x.split('.')[-1].lower() in vid_formats]
+        ni, nv = len(images), len(videos)
+
+        self.img_size = img_size
+        self.files = images + videos
+        self.nf = ni + nv  # number of files
+        self.video_flag = [False] * ni + [True] * nv
+        self.mode = 'image'
+        if any(videos):
+            self.new_video(videos[0])  # new video
+        else:
+            self.cap = None
+        assert self.nf > 0, 'No images or videos found in %s. Supported formats are:\nimages: %s\nvideos: %s' % \
+                            (p, img_formats, vid_formats)
+
+    def __iter__(self):
+        self.count = 0
+        return self
+
+    def __next__(self):
+        if self.count == self.nf:
+            raise StopIteration
+        path = self.files[self.count]
+
+        if self.video_flag[self.count]:
+            # Read video
+            self.mode = 'video'
+            ret_val, img0 = self.cap.read()
+            if not ret_val:
+                self.count += 1
+                self.cap.release()
+                if self.count == self.nf:  # last video
+                    raise StopIteration
+                else:
+                    path = self.files[self.count]
+                    self.new_video(path)
+                    ret_val, img0 = self.cap.read()
+
+            self.frame += 1
+            # print('video %g/%g (%g/%g) %s: ' % (self.count + 1, self.nf, self.frame, self.nframes, path), end='')
+            print('video %g/%g (%g/%g) : ' % (self.count + 1, self.nf, self.frame, self.nframes), end='')
+
+        else:
+            # Read image
+            self.count += 1
+            img0 = cv2.imread(path)  # BGR
+            assert img0 is not None, 'Image Not Found ' + path
+            print('image %g/%g %s: ' % (self.count, self.nf, path), end='')
+
+        # Padded resize
+        img = letterbox(img0, new_shape=self.img_size)[0]
+
+        # Convert
+        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+        img = np.ascontiguousarray(img)
+
+        return path, img, img0, self.cap
+
+    def new_video(self, path):
+        self.frame = 0
+        self.cap = cv2.VideoCapture(path)
+        self.nframes = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    def __len__(self):
+        return self.nf  # number of files
+
+
+class LoadWebcam:  # for inference
+    def __init__(self, pipe='0', img_size=640):
+        self.img_size = img_size
+
+        if pipe.isnumeric():
+            pipe = eval(pipe)  # local camera
+        # pipe = 'rtsp://192.168.1.64/1'  # IP camera
+        # pipe = 'rtsp://username:password@192.168.1.64/1'  # IP camera with login
+        # pipe = 'http://wmccpinetop.axiscam.net/mjpg/video.mjpg'  # IP golf camera
+
+        self.pipe = pipe
+        self.cap = cv2.VideoCapture(pipe)  # video capture object
+        self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3)  # set buffer size
+
+    def __iter__(self):
+        self.count = -1
+        return self
+
+    def __next__(self):
+        self.count += 1
+        if cv2.waitKey(1) == ord('q'):  # q to quit
+            self.cap.release()
+            cv2.destroyAllWindows()
+            raise StopIteration
+
+        # Read frame
+        if self.pipe == 0:  # local camera
+            ret_val, img0 = self.cap.read()
+            img0 = cv2.flip(img0, 1)  # flip left-right
+        else:  # IP camera
+            n = 0
+            while True:
+                n += 1
+                self.cap.grab()
+                if n % 30 == 0:  # skip frames
+                    ret_val, img0 = self.cap.retrieve()
+                    if ret_val:
+                        break
+
+        # Print
+        assert ret_val, 'Camera Error %s' % self.pipe
+        img_path = 'webcam.jpg'
+        print('webcam %g: ' % self.count, end='')
+
+        # Padded resize
+        img = letterbox(img0, new_shape=self.img_size)[0]
+
+        # Convert
+        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+        img = np.ascontiguousarray(img)
+
+        return img_path, img, img0, None
+
+    def __len__(self):
+        return 0
+
+
+class LoadStreams:  # multiple IP or RTSP cameras
+    def __init__(self, sources='streams.txt', img_size=640):
+        self.mode = 'stream'
+        self.img_size = img_size
+
+        if os.path.isfile(sources):
+            with open(sources, 'r') as f:
+                sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
+        else:
+            sources = [sources]
+
+        n = len(sources)
+        self.imgs = [None] * n
+        self.sources = [clean_str(x) for x in sources]  # clean source names for later
+        for i, s in enumerate(sources):
+            # Start the thread to read frames from the video stream
+            print('%g/%g: %s... ' % (i + 1, n, s), end='')
+            cap = cv2.VideoCapture(eval(s) if s.isnumeric() else s)
+            assert cap.isOpened(), 'Failed to open %s' % s
+            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            fps = cap.get(cv2.CAP_PROP_FPS) % 100
+            _, self.imgs[i] = cap.read()  # guarantee first frame
+            thread = Thread(target=self.update, args=([i, cap]), daemon=True)
+            print(' success (%gx%g at %.2f FPS).' % (w, h, fps))
+            thread.start()
+        print('')  # newline
+
+        # check for common shapes
+        s = np.stack([letterbox(x, new_shape=self.img_size)[0].shape for x in self.imgs], 0)  # inference shapes
+        self.rect = np.unique(s, axis=0).shape[0] == 1  # rect inference if all shapes equal
+        if not self.rect:
+            print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.')
+
+    def update(self, index, cap):
+        # Read next stream frame in a daemon thread
+        n = 0
+        while cap.isOpened():
+            n += 1
+            # _, self.imgs[index] = cap.read()
+            cap.grab()
+            if n == 4:  # read every 4th frame
+                _, self.imgs[index] = cap.retrieve()
+                n = 0
+            time.sleep(0.01)  # wait time
+
+    def __iter__(self):
+        self.count = -1
+        return self
+
+    def __next__(self):
+        self.count += 1
+        img0 = self.imgs.copy()
+        if cv2.waitKey(1) == ord('q'):  # q to quit
+            cv2.destroyAllWindows()
+            raise StopIteration
+
+        # Letterbox
+        img = [letterbox(x, new_shape=self.img_size, auto=self.rect)[0] for x in img0]
+
+        # Stack
+        img = np.stack(img, 0)
+
+        # Convert
+        img = img[:, :, :, ::-1].transpose(0, 3, 1, 2)  # BGR to RGB, to bsx3x416x416
+        img = np.ascontiguousarray(img)
+
+        return self.sources, img, img0, None
+
+    def __len__(self):
+        return 0  # 1E12 frames = 32 streams at 30 FPS for 30 years
+
+
+def img2label_paths(img_paths):
+    # Define label paths as a function of image paths
+    sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep  # /images/, /labels/ substrings
+    return [x.replace(sa, sb, 1).replace('.' + x.split('.')[-1], '.txt') for x in img_paths]
+
+
+class LoadImagesAndLabels(Dataset):  # for training/testing
+    def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
+                 cache_images=False, single_cls=False, stride=32, pad=0.0, rank=-1):
+        self.img_size = img_size
+        self.augment = augment
+        self.hyp = hyp
+        self.image_weights = image_weights
+        self.rect = False if image_weights else rect
+        self.mosaic = self.augment and not self.rect  # load 4 images at a time into a mosaic (only during training)
+        self.mosaic_border = [-img_size // 2, -img_size // 2]
+        self.stride = stride
+
+        try:
+            f = []  # image files
+            for p in path if isinstance(path, list) else [path]:
+                p = Path(p)  # os-agnostic
+                if p.is_dir():  # dir
+                    f += glob.glob(str(p / '**' / '*.*'), recursive=True)
+                elif p.is_file():  # file
+                    with open(p, 'r') as t:
+                        t = t.read().strip().splitlines()
+                        parent = str(p.parent) + os.sep
+                        f += [x.replace('./', parent) if x.startswith('./') else x for x in t]  # local to global path
+                else:
+                    raise Exception('%s does not exist' % p)
+            self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in img_formats])
+            assert self.img_files, 'No images found'
+        except Exception as e:
+            raise Exception('Error loading data from %s: %s\nSee %s' % (path, e, help_url))
+
+        # Check cache
+        self.label_files = img2label_paths(self.img_files)  # labels
+        cache_path = Path(self.label_files[0]).parent.with_suffix('.cache')  # cached labels
+        if cache_path.is_file():
+            cache = torch.load(cache_path)  # load
+            if cache['hash'] != get_hash(self.label_files + self.img_files) or 'results' not in cache:  # changed
+                cache = self.cache_labels(cache_path)  # re-cache
+        else:
+            cache = self.cache_labels(cache_path)  # cache
+
+        # Display cache
+        [nf, nm, ne, nc, n] = cache.pop('results')  # found, missing, empty, corrupted, total
+        desc = f"Scanning '{cache_path}' for images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupted"
+        tqdm(None, desc=desc, total=n, initial=n)
+        assert nf > 0 or not augment, f'No labels found in {cache_path}. Can not train without labels. See {help_url}'
+
+        # Read cache
+        cache.pop('hash')  # remove hash
+        labels, shapes = zip(*cache.values())
+        self.labels = list(labels)
+        self.shapes = np.array(shapes, dtype=np.float64)
+        self.img_files = list(cache.keys())  # update
+        self.label_files = img2label_paths(cache.keys())  # update
+        if single_cls:
+            for x in self.labels:
+                x[:, 0] = 0
+
+        n = len(shapes)  # number of images
+        bi = np.floor(np.arange(n) / batch_size).astype(np.int)  # batch index
+        nb = bi[-1] + 1  # number of batches
+        self.batch = bi  # batch index of image
+        self.n = n
+        self.indices = range(n)
+
+        # Rectangular Training
+        if self.rect:
+            # Sort by aspect ratio
+            s = self.shapes  # wh
+            ar = s[:, 1] / s[:, 0]  # aspect ratio
+            irect = ar.argsort()
+            self.img_files = [self.img_files[i] for i in irect]
+            self.label_files = [self.label_files[i] for i in irect]
+            self.labels = [self.labels[i] for i in irect]
+            self.shapes = s[irect]  # wh
+            ar = ar[irect]
+
+            # Set training image shapes
+            shapes = [[1, 1]] * nb
+            for i in range(nb):
+                ari = ar[bi == i]
+                mini, maxi = ari.min(), ari.max()
+                if maxi < 1:
+                    shapes[i] = [maxi, 1]
+                elif mini > 1:
+                    shapes[i] = [1, 1 / mini]
+
+            self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride
+
+        # Cache images into memory for faster training (WARNING: large datasets may exceed system RAM)
+        self.imgs = [None] * n
+        if cache_images:
+            gb = 0  # Gigabytes of cached images
+            self.img_hw0, self.img_hw = [None] * n, [None] * n
+            results = ThreadPool(8).imap(lambda x: load_image(*x), zip(repeat(self), range(n)))  # 8 threads
+            pbar = tqdm(enumerate(results), total=n)
+            for i, x in pbar:
+                self.imgs[i], self.img_hw0[i], self.img_hw[i] = x  # img, hw_original, hw_resized = load_image(self, i)
+                gb += self.imgs[i].nbytes
+                pbar.desc = 'Caching images (%.1fGB)' % (gb / 1E9)
+
+    def cache_labels(self, path=Path('./labels.cache')):
+        # Cache dataset labels, check images and read shapes
+        x = {}  # dict
+        nm, nf, ne, nc = 0, 0, 0, 0  # number missing, found, empty, duplicate
+        pbar = tqdm(zip(self.img_files, self.label_files), desc='Scanning images', total=len(self.img_files))
+        for i, (im_file, lb_file) in enumerate(pbar):
+            try:
+                # verify images
+                im = Image.open(im_file)
+                im.verify()  # PIL verify
+                shape = exif_size(im)  # image size
+                assert (shape[0] > 9) & (shape[1] > 9), 'image size <10 pixels'
+
+                # verify labels
+                if os.path.isfile(lb_file):
+                    nf += 1  # label found
+                    with open(lb_file, 'r') as f:
+                        l = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32)  # labels
+                    if len(l):
+                        assert l.shape[1] == 5, 'labels require 5 columns each'
+                        assert (l >= 0).all(), 'negative labels'
+                        assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels'
+                        assert np.unique(l, axis=0).shape[0] == l.shape[0], 'duplicate labels'
+                    else:
+                        ne += 1  # label empty
+                        l = np.zeros((0, 5), dtype=np.float32)
+                else:
+                    nm += 1  # label missing
+                    l = np.zeros((0, 5), dtype=np.float32)
+                x[im_file] = [l, shape]
+            except Exception as e:
+                nc += 1
+                print('WARNING: Ignoring corrupted image and/or label %s: %s' % (im_file, e))
+
+            pbar.desc = f"Scanning '{path.parent / path.stem}' for images and labels... " \
+                        f"{nf} found, {nm} missing, {ne} empty, {nc} corrupted"
+
+        if nf == 0:
+            print(f'WARNING: No labels found in {path}. See {help_url}')
+
+        x['hash'] = get_hash(self.label_files + self.img_files)
+        x['results'] = [nf, nm, ne, nc, i + 1]
+        torch.save(x, path)  # save for next time
+        logging.info(f"New cache created: {path}")
+        return x
+
+    def __len__(self):
+        return len(self.img_files)
+
+    # def __iter__(self):
+    #     self.count = -1
+    #     print('ran dataset iter')
+    #     #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
+    #     return self
+
+    def __getitem__(self, index):
+        index = self.indices[index]  # linear, shuffled, or image_weights
+
+        hyp = self.hyp
+        mosaic = self.mosaic and random.random() < hyp['mosaic']
+        if mosaic:
+            # Load mosaic
+            img, labels = load_mosaic(self, index)
+            shapes = None
+
+            # MixUp https://arxiv.org/pdf/1710.09412.pdf
+            if random.random() < hyp['mixup']:
+                img2, labels2 = load_mosaic(self, random.randint(0, self.n - 1))
+                r = np.random.beta(8.0, 8.0)  # mixup ratio, alpha=beta=8.0
+                img = (img * r + img2 * (1 - r)).astype(np.uint8)
+                labels = np.concatenate((labels, labels2), 0)
+
+        else:
+            # Load image
+            img, (h0, w0), (h, w) = load_image(self, index)
+
+            # Letterbox
+            shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size  # final letterboxed shape
+            img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
+            shapes = (h0, w0), ((h / h0, w / w0), pad)  # for COCO mAP rescaling
+
+            # Load labels
+            labels = []
+            x = self.labels[index]
+            if x.size > 0:
+                # Normalized xywh to pixel xyxy format
+                labels = x.copy()
+                labels[:, 1] = ratio[0] * w * (x[:, 1] - x[:, 3] / 2) + pad[0]  # pad width
+                labels[:, 2] = ratio[1] * h * (x[:, 2] - x[:, 4] / 2) + pad[1]  # pad height
+                labels[:, 3] = ratio[0] * w * (x[:, 1] + x[:, 3] / 2) + pad[0]
+                labels[:, 4] = ratio[1] * h * (x[:, 2] + x[:, 4] / 2) + pad[1]
+
+        if self.augment:
+            # Augment imagespace
+            if not mosaic:
+                img, labels = random_perspective(img, labels,
+                                                 degrees=hyp['degrees'],
+                                                 translate=hyp['translate'],
+                                                 scale=hyp['scale'],
+                                                 shear=hyp['shear'],
+                                                 perspective=hyp['perspective'])
+
+            # Augment colorspace
+            augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
+
+            # Apply cutouts
+            # if random.random() < 0.9:
+            #     labels = cutout(img, labels)
+
+        nL = len(labels)  # number of labels
+        if nL:
+            labels[:, 1:5] = xyxy2xywh(labels[:, 1:5])  # convert xyxy to xywh
+            labels[:, [2, 4]] /= img.shape[0]  # normalized height 0-1
+            labels[:, [1, 3]] /= img.shape[1]  # normalized width 0-1
+
+        if self.augment:
+            # flip up-down
+            if random.random() < hyp['flipud']:
+                img = np.flipud(img)
+                if nL:
+                    labels[:, 2] = 1 - labels[:, 2]
+
+            # flip left-right
+            if random.random() < hyp['fliplr']:
+                img = np.fliplr(img)
+                if nL:
+                    labels[:, 1] = 1 - labels[:, 1]
+
+        labels_out = torch.zeros((nL, 6))
+        if nL:
+            labels_out[:, 1:] = torch.from_numpy(labels)
+
+        # Convert
+        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+        img = np.ascontiguousarray(img)
+
+        return torch.from_numpy(img), labels_out, self.img_files[index], shapes
+
+    @staticmethod
+    def collate_fn(batch):
+        img, label, path, shapes = zip(*batch)  # transposed
+        for i, l in enumerate(label):
+            l[:, 0] = i  # add target image index for build_targets()
+        return torch.stack(img, 0), torch.cat(label, 0), path, shapes
+
+
+# Ancillary functions --------------------------------------------------------------------------------------------------
+def load_image(self, index):
+    # loads 1 image from dataset, returns img, original hw, resized hw
+    img = self.imgs[index]
+    if img is None:  # not cached
+        path = self.img_files[index]
+        img = cv2.imread(path)  # BGR
+        assert img is not None, 'Image Not Found ' + path
+        h0, w0 = img.shape[:2]  # orig hw
+        r = self.img_size / max(h0, w0)  # resize image to img_size
+        if r != 1:  # always resize down, only resize up if training with augmentation
+            interp = cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR
+            img = cv2.resize(img, (int(w0 * r), int(h0 * r)), interpolation=interp)
+        return img, (h0, w0), img.shape[:2]  # img, hw_original, hw_resized
+    else:
+        return self.imgs[index], self.img_hw0[index], self.img_hw[index]  # img, hw_original, hw_resized
+
+
+def augment_hsv(img, hgain=0.5, sgain=0.5, vgain=0.5):
+    r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1  # random gains
+    hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV))
+    dtype = img.dtype  # uint8
+
+    x = np.arange(0, 256, dtype=np.int16)
+    lut_hue = ((x * r[0]) % 180).astype(dtype)
+    lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
+    lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
+
+    img_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))).astype(dtype)
+    cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img)  # no return needed
+
+    # Histogram equalization
+    # if random.random() < 0.2:
+    #     for i in range(3):
+    #         img[:, :, i] = cv2.equalizeHist(img[:, :, i])
+
+
+def load_mosaic(self, index):
+    # loads images in a mosaic
+
+    labels4 = []
+    s = self.img_size
+    yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border]  # mosaic center x, y
+    indices = [index] + [self.indices[random.randint(0, self.n - 1)] for _ in range(3)]  # 3 additional image indices
+    for i, index in enumerate(indices):
+        # Load image
+        img, _, (h, w) = load_image(self, index)
+
+        # place img in img4
+        if i == 0:  # top left
+            img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
+            x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
+            x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
+        elif i == 1:  # top right
+            x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
+            x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
+        elif i == 2:  # bottom left
+            x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
+            x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
+        elif i == 3:  # bottom right
+            x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
+            x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
+
+        img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
+        padw = x1a - x1b
+        padh = y1a - y1b
+
+        # Labels
+        x = self.labels[index]
+        labels = x.copy()
+        if x.size > 0:  # Normalized xywh to pixel xyxy format
+            labels[:, 1] = w * (x[:, 1] - x[:, 3] / 2) + padw
+            labels[:, 2] = h * (x[:, 2] - x[:, 4] / 2) + padh
+            labels[:, 3] = w * (x[:, 1] + x[:, 3] / 2) + padw
+            labels[:, 4] = h * (x[:, 2] + x[:, 4] / 2) + padh
+        labels4.append(labels)
+
+    # Concat/clip labels
+    if len(labels4):
+        labels4 = np.concatenate(labels4, 0)
+        np.clip(labels4[:, 1:], 0, 2 * s, out=labels4[:, 1:])  # use with random_perspective
+        # img4, labels4 = replicate(img4, labels4)  # replicate
+
+    # Augment
+    img4, labels4 = random_perspective(img4, labels4,
+                                       degrees=self.hyp['degrees'],
+                                       translate=self.hyp['translate'],
+                                       scale=self.hyp['scale'],
+                                       shear=self.hyp['shear'],
+                                       perspective=self.hyp['perspective'],
+                                       border=self.mosaic_border)  # border to remove
+
+    return img4, labels4
+
+
+def replicate(img, labels):
+    # Replicate labels
+    h, w = img.shape[:2]
+    boxes = labels[:, 1:].astype(int)
+    x1, y1, x2, y2 = boxes.T
+    s = ((x2 - x1) + (y2 - y1)) / 2  # side length (pixels)
+    for i in s.argsort()[:round(s.size * 0.5)]:  # smallest indices
+        x1b, y1b, x2b, y2b = boxes[i]
+        bh, bw = y2b - y1b, x2b - x1b
+        yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw))  # offset x, y
+        x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
+        img[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
+        labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
+
+    return img, labels
+
+
+def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):
+    # Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232
+    shape = img.shape[:2]  # current shape [height, width]
+    if isinstance(new_shape, int):
+        new_shape = (new_shape, new_shape)
+
+    # Scale ratio (new / old)
+    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
+    if not scaleup:  # only scale down, do not scale up (for better test mAP)
+        r = min(r, 1.0)
+
+    # Compute padding
+    ratio = r, r  # width, height ratios
+    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
+    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
+    if auto:  # minimum rectangle
+        dw, dh = np.mod(dw, 32), np.mod(dh, 32)  # wh padding
+    elif scaleFill:  # stretch
+        dw, dh = 0.0, 0.0
+        new_unpad = (new_shape[1], new_shape[0])
+        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios
+
+    dw /= 2  # divide padding into 2 sides
+    dh /= 2
+
+    if shape[::-1] != new_unpad:  # resize
+        img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
+    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
+    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
+    img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
+    return img, ratio, (dw, dh)
+
+
+def random_perspective(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0, border=(0, 0)):
+    # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
+    # targets = [cls, xyxy]
+
+    height = img.shape[0] + border[0] * 2  # shape(h,w,c)
+    width = img.shape[1] + border[1] * 2
+
+    # Center
+    C = np.eye(3)
+    C[0, 2] = -img.shape[1] / 2  # x translation (pixels)
+    C[1, 2] = -img.shape[0] / 2  # y translation (pixels)
+
+    # Perspective
+    P = np.eye(3)
+    P[2, 0] = random.uniform(-perspective, perspective)  # x perspective (about y)
+    P[2, 1] = random.uniform(-perspective, perspective)  # y perspective (about x)
+
+    # Rotation and Scale
+    R = np.eye(3)
+    a = random.uniform(-degrees, degrees)
+    # a += random.choice([-180, -90, 0, 90])  # add 90deg rotations to small rotations
+    s = random.uniform(1 - scale, 1 + scale)
+    # s = 2 ** random.uniform(-scale, scale)
+    R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
+
+    # Shear
+    S = np.eye(3)
+    S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # x shear (deg)
+    S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # y shear (deg)
+
+    # Translation
+    T = np.eye(3)
+    T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width  # x translation (pixels)
+    T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height  # y translation (pixels)
+
+    # Combined rotation matrix
+    M = T @ S @ R @ P @ C  # order of operations (right to left) is IMPORTANT
+    if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed
+        if perspective:
+            img = cv2.warpPerspective(img, M, dsize=(width, height), borderValue=(114, 114, 114))
+        else:  # affine
+            img = cv2.warpAffine(img, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
+
+    # Visualize
+    # import matplotlib.pyplot as plt
+    # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
+    # ax[0].imshow(img[:, :, ::-1])  # base
+    # ax[1].imshow(img2[:, :, ::-1])  # warped
+
+    # Transform label coordinates
+    n = len(targets)
+    if n:
+        # warp points
+        xy = np.ones((n * 4, 3))
+        xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2)  # x1y1, x2y2, x1y2, x2y1
+        xy = xy @ M.T  # transform
+        if perspective:
+            xy = (xy[:, :2] / xy[:, 2:3]).reshape(n, 8)  # rescale
+        else:  # affine
+            xy = xy[:, :2].reshape(n, 8)
+
+        # create new boxes
+        x = xy[:, [0, 2, 4, 6]]
+        y = xy[:, [1, 3, 5, 7]]
+        xy = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
+
+        # # apply angle-based reduction of bounding boxes
+        # radians = a * math.pi / 180
+        # reduction = max(abs(math.sin(radians)), abs(math.cos(radians))) ** 0.5
+        # x = (xy[:, 2] + xy[:, 0]) / 2
+        # y = (xy[:, 3] + xy[:, 1]) / 2
+        # w = (xy[:, 2] - xy[:, 0]) * reduction
+        # h = (xy[:, 3] - xy[:, 1]) * reduction
+        # xy = np.concatenate((x - w / 2, y - h / 2, x + w / 2, y + h / 2)).reshape(4, n).T
+
+        # clip boxes
+        xy[:, [0, 2]] = xy[:, [0, 2]].clip(0, width)
+        xy[:, [1, 3]] = xy[:, [1, 3]].clip(0, height)
+
+        # filter candidates
+        i = box_candidates(box1=targets[:, 1:5].T * s, box2=xy.T)
+        targets = targets[i]
+        targets[:, 1:5] = xy[i]
+
+    return img, targets
+
+
+def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1):  # box1(4,n), box2(4,n)
+    # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
+    w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
+    w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
+    ar = np.maximum(w2 / (h2 + 1e-16), h2 / (w2 + 1e-16))  # aspect ratio
+    return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + 1e-16) > area_thr) & (ar < ar_thr)  # candidates
+
+
+def cutout(image, labels):
+    # Applies image cutout augmentation https://arxiv.org/abs/1708.04552
+    h, w = image.shape[:2]
+
+    def bbox_ioa(box1, box2):
+        # Returns the intersection over box2 area given box1, box2. box1 is 4, box2 is nx4. boxes are x1y1x2y2
+        box2 = box2.transpose()
+
+        # Get the coordinates of bounding boxes
+        b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
+        b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
+
+        # Intersection area
+        inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \
+                     (np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0)
+
+        # box2 area
+        box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + 1e-16
+
+        # Intersection over box2 area
+        return inter_area / box2_area
+
+    # create random masks
+    scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16  # image size fraction
+    for s in scales:
+        mask_h = random.randint(1, int(h * s))
+        mask_w = random.randint(1, int(w * s))
+
+        # box
+        xmin = max(0, random.randint(0, w) - mask_w // 2)
+        ymin = max(0, random.randint(0, h) - mask_h // 2)
+        xmax = min(w, xmin + mask_w)
+        ymax = min(h, ymin + mask_h)
+
+        # apply random color mask
+        image[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
+
+        # return unobscured labels
+        if len(labels) and s > 0.03:
+            box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32)
+            ioa = bbox_ioa(box, labels[:, 1:5])  # intersection over area
+            labels = labels[ioa < 0.60]  # remove >60% obscured labels
+
+    return labels
+
+
+def create_folder(path='./new'):
+    # Create folder
+    if os.path.exists(path):
+        shutil.rmtree(path)  # delete output folder
+    os.makedirs(path)  # make new output folder
+
+
+def flatten_recursive(path='../coco128'):
+    # Flatten a recursive directory by bringing all files to top level
+    new_path = Path(path + '_flat')
+    create_folder(new_path)
+    for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)):
+        shutil.copyfile(file, new_path / Path(file).name)
+
+
+def extract_boxes(path='../coco128/'):  # from utils.datasets import *; extract_boxes('../coco128')
+    # Convert detection dataset into classification dataset, with one directory per class
+
+    path = Path(path)  # images dir
+    shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None  # remove existing
+    files = list(path.rglob('*.*'))
+    n = len(files)  # number of files
+    for im_file in tqdm(files, total=n):
+        if im_file.suffix[1:] in img_formats:
+            # image
+            im = cv2.imread(str(im_file))[..., ::-1]  # BGR to RGB
+            h, w = im.shape[:2]
+
+            # labels
+            lb_file = Path(img2label_paths([str(im_file)])[0])
+            if Path(lb_file).exists():
+                with open(lb_file, 'r') as f:
+                    lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32)  # labels
+
+                for j, x in enumerate(lb):
+                    c = int(x[0])  # class
+                    f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg'  # new filename
+                    if not f.parent.is_dir():
+                        f.parent.mkdir(parents=True)
+
+                    b = x[1:] * [w, h, w, h]  # box
+                    # b[2:] = b[2:].max()  # rectangle to square
+                    b[2:] = b[2:] * 1.2 + 3  # pad
+                    b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int)
+
+                    b[[0, 2]] = np.clip(b[[0, 2]], 0, w)  # clip boxes outside of image
+                    b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
+                    assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'
+
+
+def autosplit(path='../coco128', weights=(0.9, 0.1, 0.0)):  # from utils.datasets import *; autosplit('../coco128')
+    """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
+    # Arguments
+        path:       Path to images directory
+        weights:    Train, val, test weights (list)
+    """
+    path = Path(path)  # images dir
+    files = list(path.rglob('*.*'))
+    n = len(files)  # number of files
+    indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split
+    txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt']  # 3 txt files
+    [(path / x).unlink() for x in txt if (path / x).exists()]  # remove existing
+    for i, img in tqdm(zip(indices, files), total=n):
+        if img.suffix[1:] in img_formats:
+            with open(path / txt[i], 'a') as f:
+                f.write(str(img) + '\n')  # add image to txt file

yolov5/utils/general.py

@@ -0,0 +1,445 @@
+# General utils
+
+import glob
+import logging
+import math
+import os
+import platform
+import random
+import re
+import subprocess
+import time
+from pathlib import Path
+
+import cv2
+import numpy as np
+import torch
+import torchvision
+import yaml
+
+from utils.google_utils import gsutil_getsize
+from utils.metrics import fitness
+from utils.torch_utils import init_torch_seeds
+
+# Settings
+torch.set_printoptions(linewidth=320, precision=5, profile='long')
+np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format})  # format short g, %precision=5
+cv2.setNumThreads(0)  # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
+
+
+def set_logging(rank=-1):
+    logging.basicConfig(
+        format="%(message)s",
+        level=logging.INFO if rank in [-1, 0] else logging.WARN)
+
+
+def init_seeds(seed=0):
+    random.seed(seed)
+    np.random.seed(seed)
+    init_torch_seeds(seed)
+
+
+def get_latest_run(search_dir='.'):
+    # Return path to most recent 'last.pt' in /runs (i.e. to --resume from)
+    last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
+    return max(last_list, key=os.path.getctime) if last_list else ''
+
+
+def check_git_status():
+    # Suggest 'git pull' if repo is out of date
+    if platform.system() in ['Linux', 'Darwin'] and not os.path.isfile('/.dockerenv'):
+        s = subprocess.check_output('if [ -d .git ]; then git fetch && git status -uno; fi', shell=True).decode('utf-8')
+        if 'Your branch is behind' in s:
+            print(s[s.find('Your branch is behind'):s.find('\n\n')] + '\n')
+
+
+def check_img_size(img_size, s=32):
+    # Verify img_size is a multiple of stride s
+    new_size = make_divisible(img_size, int(s))  # ceil gs-multiple
+    if new_size != img_size:
+        print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size))
+    return new_size
+
+
+def check_file(file):
+    # Search for file if not found
+    if os.path.isfile(file) or file == '':
+        return file
+    else:
+        files = glob.glob('./**/' + file, recursive=True)  # find file
+        assert len(files), 'File Not Found: %s' % file  # assert file was found
+        assert len(files) == 1, "Multiple files match '%s', specify exact path: %s" % (file, files)  # assert unique
+        return files[0]  # return file
+
+
+def check_dataset(dict):
+    # Download dataset if not found locally
+    val, s = dict.get('val'), dict.get('download')
+    if val and len(val):
+        val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])]  # val path
+        if not all(x.exists() for x in val):
+            print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()])
+            if s and len(s):  # download script
+                print('Downloading %s ...' % s)
+                if s.startswith('http') and s.endswith('.zip'):  # URL
+                    f = Path(s).name  # filename
+                    torch.hub.download_url_to_file(s, f)
+                    r = os.system('unzip -q %s -d ../ && rm %s' % (f, f))  # unzip
+                else:  # bash script
+                    r = os.system(s)
+                print('Dataset autodownload %s\n' % ('success' if r == 0 else 'failure'))  # analyze return value
+            else:
+                raise Exception('Dataset not found.')
+
+
+def make_divisible(x, divisor):
+    # Returns x evenly divisible by divisor
+    return math.ceil(x / divisor) * divisor
+
+
+def clean_str(s):
+    # Cleans a string by replacing special characters with underscore _
+    return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)
+
+
+def labels_to_class_weights(labels, nc=80):
+    # Get class weights (inverse frequency) from training labels
+    if labels[0] is None:  # no labels loaded
+        return torch.Tensor()
+
+    labels = np.concatenate(labels, 0)  # labels.shape = (866643, 5) for COCO
+    classes = labels[:, 0].astype(np.int)  # labels = [class xywh]
+    weights = np.bincount(classes, minlength=nc)  # occurrences per class
+
+    # Prepend gridpoint count (for uCE training)
+    # gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum()  # gridpoints per image
+    # weights = np.hstack([gpi * len(labels)  - weights.sum() * 9, weights * 9]) ** 0.5  # prepend gridpoints to start
+
+    weights[weights == 0] = 1  # replace empty bins with 1
+    weights = 1 / weights  # number of targets per class
+    weights /= weights.sum()  # normalize
+    return torch.from_numpy(weights)
+
+
+def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)):
+    # Produces image weights based on class_weights and image contents
+    class_counts = np.array([np.bincount(x[:, 0].astype(np.int), minlength=nc) for x in labels])
+    image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1)
+    # index = random.choices(range(n), weights=image_weights, k=1)  # weight image sample
+    return image_weights
+
+
+def coco80_to_coco91_class():  # converts 80-index (val2014) to 91-index (paper)
+    # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/
+    # a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
+    # b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
+    # x1 = [list(a[i] == b).index(True) + 1 for i in range(80)]  # darknet to coco
+    # x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)]  # coco to darknet
+    x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
+         35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
+         64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
+    return x
+
+
+def xyxy2xywh(x):
+    # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = (x[:, 0] + x[:, 2]) / 2  # x center
+    y[:, 1] = (x[:, 1] + x[:, 3]) / 2  # y center
+    y[:, 2] = x[:, 2] - x[:, 0]  # width
+    y[:, 3] = x[:, 3] - x[:, 1]  # height
+    return y
+
+
+def xywh2xyxy(x):
+    # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
+    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
+    y[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right x
+    y[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right y
+    return y
+
+
+def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
+    # Rescale coords (xyxy) from img1_shape to img0_shape
+    if ratio_pad is None:  # calculate from img0_shape
+        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
+        pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
+    else:
+        gain = ratio_pad[0][0]
+        pad = ratio_pad[1]
+
+    coords[:, [0, 2]] -= pad[0]  # x padding
+    coords[:, [1, 3]] -= pad[1]  # y padding
+    coords[:, :4] /= gain
+    clip_coords(coords, img0_shape)
+    return coords
+
+
+def clip_coords(boxes, img_shape):
+    # Clip bounding xyxy bounding boxes to image shape (height, width)
+    boxes[:, 0].clamp_(0, img_shape[1])  # x1
+    boxes[:, 1].clamp_(0, img_shape[0])  # y1
+    boxes[:, 2].clamp_(0, img_shape[1])  # x2
+    boxes[:, 3].clamp_(0, img_shape[0])  # y2
+
+
+def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-9):
+    # Returns the IoU of box1 to box2. box1 is 4, box2 is nx4
+    box2 = box2.T
+
+    # Get the coordinates of bounding boxes
+    if x1y1x2y2:  # x1, y1, x2, y2 = box1
+        b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
+        b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
+    else:  # transform from xywh to xyxy
+        b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
+        b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
+        b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
+        b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2
+
+    # Intersection area
+    inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
+            (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)
+
+    # Union Area
+    w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
+    w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
+    union = w1 * h1 + w2 * h2 - inter + eps
+
+    iou = inter / union
+    if GIoU or DIoU or CIoU:
+        cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1)  # convex (smallest enclosing box) width
+        ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1)  # convex height
+        if CIoU or DIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
+            c2 = cw ** 2 + ch ** 2 + eps  # convex diagonal squared
+            rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +
+                    (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4  # center distance squared
+            if DIoU:
+                return iou - rho2 / c2  # DIoU
+            elif CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
+                v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
+                with torch.no_grad():
+                    alpha = v / ((1 + eps) - iou + v)
+                return iou - (rho2 / c2 + v * alpha)  # CIoU
+        else:  # GIoU https://arxiv.org/pdf/1902.09630.pdf
+            c_area = cw * ch + eps  # convex area
+            return iou - (c_area - union) / c_area  # GIoU
+    else:
+        return iou  # IoU
+
+
+def box_iou(box1, box2):
+    # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
+    """
+    Return intersection-over-union (Jaccard index) of boxes.
+    Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
+    Arguments:
+        box1 (Tensor[N, 4])
+        box2 (Tensor[M, 4])
+    Returns:
+        iou (Tensor[N, M]): the NxM matrix containing the pairwise
+            IoU values for every element in boxes1 and boxes2
+    """
+
+    def box_area(box):
+        # box = 4xn
+        return (box[2] - box[0]) * (box[3] - box[1])
+
+    area1 = box_area(box1.T)
+    area2 = box_area(box2.T)
+
+    # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
+    inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
+    return inter / (area1[:, None] + area2 - inter)  # iou = inter / (area1 + area2 - inter)
+
+
+def wh_iou(wh1, wh2):
+    # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2
+    wh1 = wh1[:, None]  # [N,1,2]
+    wh2 = wh2[None]  # [1,M,2]
+    inter = torch.min(wh1, wh2).prod(2)  # [N,M]
+    return inter / (wh1.prod(2) + wh2.prod(2) - inter)  # iou = inter / (area1 + area2 - inter)
+
+
+def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, labels=()):
+    """Performs Non-Maximum Suppression (NMS) on inference results
+
+    Returns:
+         detections with shape: nx6 (x1, y1, x2, y2, conf, cls)
+    """
+
+    nc = prediction.shape[2] - 5  # number of classes
+    xc = prediction[..., 4] > conf_thres  # candidates
+
+    # Settings
+    min_wh, max_wh = 2, 4096  # (pixels) minimum and maximum box width and height
+    max_det = 300  # maximum number of detections per image
+    time_limit = 10.0  # seconds to quit after
+    redundant = True  # require redundant detections
+    multi_label = nc > 1  # multiple labels per box (adds 0.5ms/img)
+    merge = False  # use merge-NMS
+
+    t = time.time()
+    output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
+    for xi, x in enumerate(prediction):  # image index, image inference
+        # Apply constraints
+        # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0  # width-height
+        x = x[xc[xi]]  # confidence
+
+        # Cat apriori labels if autolabelling
+        if labels and len(labels[xi]):
+            l = labels[xi]
+            v = torch.zeros((len(l), nc + 5), device=x.device)
+            v[:, :4] = l[:, 1:5]  # box
+            v[:, 4] = 1.0  # conf
+            v[range(len(l)), l[:, 0].long() + 5] = 1.0  # cls
+            x = torch.cat((x, v), 0)
+
+        # If none remain process next image
+        if not x.shape[0]:
+            continue
+
+        # Compute conf
+        x[:, 5:] *= x[:, 4:5]  # conf = obj_conf * cls_conf
+
+        # Box (center x, center y, width, height) to (x1, y1, x2, y2)
+        box = xywh2xyxy(x[:, :4])
+
+        # Detections matrix nx6 (xyxy, conf, cls)
+        if multi_label:
+            i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
+            x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
+        else:  # best class only
+            conf, j = x[:, 5:].max(1, keepdim=True)
+            x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
+
+        # Filter by class
+        if classes is not None:
+            x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
+
+        # Apply finite constraint
+        # if not torch.isfinite(x).all():
+        #     x = x[torch.isfinite(x).all(1)]
+
+        # If none remain process next image
+        n = x.shape[0]  # number of boxes
+        if not n:
+            continue
+
+        # Sort by confidence
+        # x = x[x[:, 4].argsort(descending=True)]
+
+        # Batched NMS
+        c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
+        boxes, scores = x[:, :4] + c, x[:, 4]  # boxes (offset by class), scores
+        i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
+        if i.shape[0] > max_det:  # limit detections
+            i = i[:max_det]
+        if merge and (1 < n < 3E3):  # Merge NMS (boxes merged using weighted mean)
+            # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
+            iou = box_iou(boxes[i], boxes) > iou_thres  # iou matrix
+            weights = iou * scores[None]  # box weights
+            x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True)  # merged boxes
+            if redundant:
+                i = i[iou.sum(1) > 1]  # require redundancy
+
+        output[xi] = x[i]
+        if (time.time() - t) > time_limit:
+            break  # time limit exceeded
+
+    return output
+
+
+def strip_optimizer(f='weights/best.pt', s=''):  # from utils.general import *; strip_optimizer()
+    # Strip optimizer from 'f' to finalize training, optionally save as 's'
+    x = torch.load(f, map_location=torch.device('cpu'))
+    x['optimizer'] = None
+    x['training_results'] = None
+    x['epoch'] = -1
+    x['model'].half()  # to FP16
+    for p in x['model'].parameters():
+        p.requires_grad = False
+    torch.save(x, s or f)
+    mb = os.path.getsize(s or f) / 1E6  # filesize
+    print('Optimizer stripped from %s,%s %.1fMB' % (f, (' saved as %s,' % s) if s else '', mb))
+
+
+def print_mutation(hyp, results, yaml_file='hyp_evolved.yaml', bucket=''):
+    # Print mutation results to evolve.txt (for use with train.py --evolve)
+    a = '%10s' * len(hyp) % tuple(hyp.keys())  # hyperparam keys
+    b = '%10.3g' * len(hyp) % tuple(hyp.values())  # hyperparam values
+    c = '%10.4g' * len(results) % results  # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
+    print('\n%s\n%s\nEvolved fitness: %s\n' % (a, b, c))
+
+    if bucket:
+        url = 'gs://%s/evolve.txt' % bucket
+        if gsutil_getsize(url) > (os.path.getsize('evolve.txt') if os.path.exists('evolve.txt') else 0):
+            os.system('gsutil cp %s .' % url)  # download evolve.txt if larger than local
+
+    with open('evolve.txt', 'a') as f:  # append result
+        f.write(c + b + '\n')
+    x = np.unique(np.loadtxt('evolve.txt', ndmin=2), axis=0)  # load unique rows
+    x = x[np.argsort(-fitness(x))]  # sort
+    np.savetxt('evolve.txt', x, '%10.3g')  # save sort by fitness
+
+    # Save yaml
+    for i, k in enumerate(hyp.keys()):
+        hyp[k] = float(x[0, i + 7])
+    with open(yaml_file, 'w') as f:
+        results = tuple(x[0, :7])
+        c = '%10.4g' * len(results) % results  # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
+        f.write('# Hyperparameter Evolution Results\n# Generations: %g\n# Metrics: ' % len(x) + c + '\n\n')
+        yaml.dump(hyp, f, sort_keys=False)
+
+    if bucket:
+        os.system('gsutil cp evolve.txt %s gs://%s' % (yaml_file, bucket))  # upload
+
+
+def apply_classifier(x, model, img, im0):
+    # applies a second stage classifier to yolo outputs
+    im0 = [im0] if isinstance(im0, np.ndarray) else im0
+    for i, d in enumerate(x):  # per image
+        if d is not None and len(d):
+            d = d.clone()
+
+            # Reshape and pad cutouts
+            b = xyxy2xywh(d[:, :4])  # boxes
+            b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1)  # rectangle to square
+            b[:, 2:] = b[:, 2:] * 1.3 + 30  # pad
+            d[:, :4] = xywh2xyxy(b).long()
+
+            # Rescale boxes from img_size to im0 size
+            scale_coords(img.shape[2:], d[:, :4], im0[i].shape)
+
+            # Classes
+            pred_cls1 = d[:, 5].long()
+            ims = []
+            for j, a in enumerate(d):  # per item
+                cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])]
+                im = cv2.resize(cutout, (224, 224))  # BGR
+                # cv2.imwrite('test%i.jpg' % j, cutout)
+
+                im = im[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+                im = np.ascontiguousarray(im, dtype=np.float32)  # uint8 to float32
+                im /= 255.0  # 0 - 255 to 0.0 - 1.0
+                ims.append(im)
+
+            pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1)  # classifier prediction
+            x[i] = x[i][pred_cls1 == pred_cls2]  # retain matching class detections
+
+    return x
+
+
+def increment_path(path, exist_ok=True, sep=''):
+    # Increment path, i.e. runs/exp --> runs/exp{sep}0, runs/exp{sep}1 etc.
+    path = Path(path)  # os-agnostic
+    if (path.exists() and exist_ok) or (not path.exists()):
+        return str(path)
+    else:
+        dirs = glob.glob(f"{path}{sep}*")  # similar paths
+        matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
+        i = [int(m.groups()[0]) for m in matches if m]  # indices
+        n = max(i) + 1 if i else 2  # increment number
+        return f"{path}{sep}{n}"  # update path

yolov5/utils/google_app_engine/Dockerfile

@@ -0,0 +1,25 @@
+FROM gcr.io/google-appengine/python
+
+# Create a virtualenv for dependencies. This isolates these packages from
+# system-level packages.
+# Use -p python3 or -p python3.7 to select python version. Default is version 2.
+RUN virtualenv /env -p python3
+
+# Setting these environment variables are the same as running
+# source /env/bin/activate.
+ENV VIRTUAL_ENV /env
+ENV PATH /env/bin:$PATH
+
+RUN apt-get update && apt-get install -y python-opencv
+
+# Copy the application's requirements.txt and run pip to install all
+# dependencies into the virtualenv.
+ADD requirements.txt /app/requirements.txt
+RUN pip install -r /app/requirements.txt
+
+# Add the application source code.
+ADD . /app
+
+# Run a WSGI server to serve the application. gunicorn must be declared as
+# a dependency in requirements.txt.
+CMD gunicorn -b :$PORT main:app

yolov5/utils/google_app_engine/additional_requirements.txt

@@ -0,0 +1,4 @@
+# add these requirements in your app on top of the existing ones
+pip==18.1
+Flask==1.0.2
+gunicorn==19.9.0

yolov5/utils/google_app_engine/app.yaml

@@ -0,0 +1,14 @@
+runtime: custom
+env: flex
+
+service: yolov5app
+
+liveness_check:
+  initial_delay_sec: 600
+
+manual_scaling:
+  instances: 1
+resources:
+  cpu: 1
+  memory_gb: 4
+  disk_size_gb: 20

yolov5/utils/google_utils.py

@@ -0,0 +1,122 @@
+# Google utils: https://cloud.google.com/storage/docs/reference/libraries
+
+import os
+import platform
+import subprocess
+import time
+from pathlib import Path
+
+import torch
+
+
+def gsutil_getsize(url=''):
+    # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du
+    s = subprocess.check_output('gsutil du %s' % url, shell=True).decode('utf-8')
+    return eval(s.split(' ')[0]) if len(s) else 0  # bytes
+
+
+def attempt_download(weights):
+    # Attempt to download pretrained weights if not found locally
+    weights = str(weights).strip().replace("'", '')
+    file = Path(weights).name.lower()
+
+    msg = weights + ' missing, try downloading from https://github.com/ultralytics/yolov5/releases/'
+    models = ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']  # available models
+    redundant = False  # offer second download option
+
+    if file in models and not os.path.isfile(weights):
+        # Google Drive
+        # d = {'yolov5s.pt': '1R5T6rIyy3lLwgFXNms8whc-387H0tMQO',
+        #      'yolov5m.pt': '1vobuEExpWQVpXExsJ2w-Mbf3HJjWkQJr',
+        #      'yolov5l.pt': '1hrlqD1Wdei7UT4OgT785BEk1JwnSvNEV',
+        #      'yolov5x.pt': '1mM8aZJlWTxOg7BZJvNUMrTnA2AbeCVzS'}
+        # r = gdrive_download(id=d[file], name=weights) if file in d else 1
+        # if r == 0 and os.path.exists(weights) and os.path.getsize(weights) > 1E6:  # check
+        #    return
+
+        try:  # GitHub
+            url = 'https://github.com/ultralytics/yolov5/releases/download/v3.1/' + file
+            print('Downloading %s to %s...' % (url, weights))
+            torch.hub.download_url_to_file(url, weights)
+            assert os.path.exists(weights) and os.path.getsize(weights) > 1E6  # check
+        except Exception as e:  # GCP
+            print('Download error: %s' % e)
+            assert redundant, 'No secondary mirror'
+            url = 'https://storage.googleapis.com/ultralytics/yolov5/ckpt/' + file
+            print('Downloading %s to %s...' % (url, weights))
+            r = os.system('curl -L %s -o %s' % (url, weights))  # torch.hub.download_url_to_file(url, weights)
+        finally:
+            if not (os.path.exists(weights) and os.path.getsize(weights) > 1E6):  # check
+                os.remove(weights) if os.path.exists(weights) else None  # remove partial downloads
+                print('ERROR: Download failure: %s' % msg)
+            print('')
+            return
+
+
+def gdrive_download(id='1uH2BylpFxHKEGXKL6wJJlsgMU2YEjxuc', name='tmp.zip'):
+    # Downloads a file from Google Drive. from utils.google_utils import *; gdrive_download()
+    t = time.time()
+
+    print('Downloading https://drive.google.com/uc?export=download&id=%s as %s... ' % (id, name), end='')
+    os.remove(name) if os.path.exists(name) else None  # remove existing
+    os.remove('cookie') if os.path.exists('cookie') else None
+
+    # Attempt file download
+    out = "NUL" if platform.system() == "Windows" else "/dev/null"
+    os.system('curl -c ./cookie -s -L "drive.google.com/uc?export=download&id=%s" > %s ' % (id, out))
+    if os.path.exists('cookie'):  # large file
+        s = 'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm=%s&id=%s" -o %s' % (get_token(), id, name)
+    else:  # small file
+        s = 'curl -s -L -o %s "drive.google.com/uc?export=download&id=%s"' % (name, id)
+    r = os.system(s)  # execute, capture return
+    os.remove('cookie') if os.path.exists('cookie') else None
+
+    # Error check
+    if r != 0:
+        os.remove(name) if os.path.exists(name) else None  # remove partial
+        print('Download error ')  # raise Exception('Download error')
+        return r
+
+    # Unzip if archive
+    if name.endswith('.zip'):
+        print('unzipping... ', end='')
+        os.system('unzip -q %s' % name)  # unzip
+        os.remove(name)  # remove zip to free space
+
+    print('Done (%.1fs)' % (time.time() - t))
+    return r
+
+
+def get_token(cookie="./cookie"):
+    with open(cookie) as f:
+        for line in f:
+            if "download" in line:
+                return line.split()[-1]
+    return ""
+
+# def upload_blob(bucket_name, source_file_name, destination_blob_name):
+#     # Uploads a file to a bucket
+#     # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python
+#
+#     storage_client = storage.Client()
+#     bucket = storage_client.get_bucket(bucket_name)
+#     blob = bucket.blob(destination_blob_name)
+#
+#     blob.upload_from_filename(source_file_name)
+#
+#     print('File {} uploaded to {}.'.format(
+#         source_file_name,
+#         destination_blob_name))
+#
+#
+# def download_blob(bucket_name, source_blob_name, destination_file_name):
+#     # Uploads a blob from a bucket
+#     storage_client = storage.Client()
+#     bucket = storage_client.get_bucket(bucket_name)
+#     blob = bucket.blob(source_blob_name)
+#
+#     blob.download_to_filename(destination_file_name)
+#
+#     print('Blob {} downloaded to {}.'.format(
+#         source_blob_name,
+#         destination_file_name))

yolov5/utils/loss.py

@@ -0,0 +1,205 @@
+# Loss functions
+
+import torch
+import torch.nn as nn
+
+from utils.general import bbox_iou
+from utils.torch_utils import is_parallel
+
+
+def smooth_BCE(eps=0.1):  # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441
+    # return positive, negative label smoothing BCE targets
+    return 1.0 - 0.5 * eps, 0.5 * eps
+
+
+class BCEBlurWithLogitsLoss(nn.Module):
+    # BCEwithLogitLoss() with reduced missing label effects.
+    def __init__(self, alpha=0.05):
+        super(BCEBlurWithLogitsLoss, self).__init__()
+        self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none')  # must be nn.BCEWithLogitsLoss()
+        self.alpha = alpha
+
+    def forward(self, pred, true):
+        loss = self.loss_fcn(pred, true)
+        pred = torch.sigmoid(pred)  # prob from logits
+        dx = pred - true  # reduce only missing label effects
+        # dx = (pred - true).abs()  # reduce missing label and false label effects
+        alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4))
+        loss *= alpha_factor
+        return loss.mean()
+
+
+class FocalLoss(nn.Module):
+    # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
+    def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
+        super(FocalLoss, self).__init__()
+        self.loss_fcn = loss_fcn  # must be nn.BCEWithLogitsLoss()
+        self.gamma = gamma
+        self.alpha = alpha
+        self.reduction = loss_fcn.reduction
+        self.loss_fcn.reduction = 'none'  # required to apply FL to each element
+
+    def forward(self, pred, true):
+        loss = self.loss_fcn(pred, true)
+        # p_t = torch.exp(-loss)
+        # loss *= self.alpha * (1.000001 - p_t) ** self.gamma  # non-zero power for gradient stability
+
+        # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
+        pred_prob = torch.sigmoid(pred)  # prob from logits
+        p_t = true * pred_prob + (1 - true) * (1 - pred_prob)
+        alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
+        modulating_factor = (1.0 - p_t) ** self.gamma
+        loss *= alpha_factor * modulating_factor
+
+        if self.reduction == 'mean':
+            return loss.mean()
+        elif self.reduction == 'sum':
+            return loss.sum()
+        else:  # 'none'
+            return loss
+
+
+class QFocalLoss(nn.Module):
+    # Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
+    def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
+        super(QFocalLoss, self).__init__()
+        self.loss_fcn = loss_fcn  # must be nn.BCEWithLogitsLoss()
+        self.gamma = gamma
+        self.alpha = alpha
+        self.reduction = loss_fcn.reduction
+        self.loss_fcn.reduction = 'none'  # required to apply FL to each element
+
+    def forward(self, pred, true):
+        loss = self.loss_fcn(pred, true)
+
+        pred_prob = torch.sigmoid(pred)  # prob from logits
+        alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
+        modulating_factor = torch.abs(true - pred_prob) ** self.gamma
+        loss *= alpha_factor * modulating_factor
+
+        if self.reduction == 'mean':
+            return loss.mean()
+        elif self.reduction == 'sum':
+            return loss.sum()
+        else:  # 'none'
+            return loss
+
+
+def compute_loss(p, targets, model):  # predictions, targets, model
+    device = targets.device
+    lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device)
+    tcls, tbox, indices, anchors = build_targets(p, targets, model)  # targets
+    h = model.hyp  # hyperparameters
+
+    # Define criteria
+    BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device))  # weight=model.class_weights)
+    BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device))
+
+    # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
+    cp, cn = smooth_BCE(eps=0.0)
+
+    # Focal loss
+    g = h['fl_gamma']  # focal loss gamma
+    if g > 0:
+        BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
+
+    # Losses
+    nt = 0  # number of targets
+    no = len(p)  # number of outputs
+    balance = [4.0, 1.0, 0.4] if no == 3 else [4.0, 1.0, 0.4, 0.1]  # P3-5 or P3-6
+    for i, pi in enumerate(p):  # layer index, layer predictions
+        b, a, gj, gi = indices[i]  # image, anchor, gridy, gridx
+        tobj = torch.zeros_like(pi[..., 0], device=device)  # target obj
+
+        n = b.shape[0]  # number of targets
+        if n:
+            nt += n  # cumulative targets
+            ps = pi[b, a, gj, gi]  # prediction subset corresponding to targets
+
+            # Regression
+            pxy = ps[:, :2].sigmoid() * 2. - 0.5
+            pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
+            pbox = torch.cat((pxy, pwh), 1)  # predicted box
+            iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True)  # iou(prediction, target)
+            lbox += (1.0 - iou).mean()  # iou loss
+
+            # Objectness
+            tobj[b, a, gj, gi] = (1.0 - model.gr) + model.gr * iou.detach().clamp(0).type(tobj.dtype)  # iou ratio
+
+            # Classification
+            if model.nc > 1:  # cls loss (only if multiple classes)
+                t = torch.full_like(ps[:, 5:], cn, device=device)  # targets
+                t[range(n), tcls[i]] = cp
+                lcls += BCEcls(ps[:, 5:], t)  # BCE
+
+            # Append targets to text file
+            # with open('targets.txt', 'a') as file:
+            #     [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]
+
+        lobj += BCEobj(pi[..., 4], tobj) * balance[i]  # obj loss
+
+    s = 3 / no  # output count scaling
+    lbox *= h['box'] * s
+    lobj *= h['obj'] * s * (1.4 if no == 4 else 1.)
+    lcls *= h['cls'] * s
+    bs = tobj.shape[0]  # batch size
+
+    loss = lbox + lobj + lcls
+    return loss * bs, torch.cat((lbox, lobj, lcls, loss)).detach()
+
+
+def build_targets(p, targets, model):
+    # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
+    det = model.module.model[-1] if is_parallel(model) else model.model[-1]  # Detect() module
+    na, nt = det.na, targets.shape[0]  # number of anchors, targets
+    tcls, tbox, indices, anch = [], [], [], []
+    gain = torch.ones(7, device=targets.device)  # normalized to gridspace gain
+    ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt)  # same as .repeat_interleave(nt)
+    targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2)  # append anchor indices
+
+    g = 0.5  # bias
+    off = torch.tensor([[0, 0],
+                        [1, 0], [0, 1], [-1, 0], [0, -1],  # j,k,l,m
+                        # [1, 1], [1, -1], [-1, 1], [-1, -1],  # jk,jm,lk,lm
+                        ], device=targets.device).float() * g  # offsets
+
+    for i in range(det.nl):
+        anchors = det.anchors[i]
+        gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]]  # xyxy gain
+
+        # Match targets to anchors
+        t = targets * gain
+        if nt:
+            # Matches
+            r = t[:, :, 4:6] / anchors[:, None]  # wh ratio
+            j = torch.max(r, 1. / r).max(2)[0] < model.hyp['anchor_t']  # compare
+            # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t']  # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
+            t = t[j]  # filter
+
+            # Offsets
+            gxy = t[:, 2:4]  # grid xy
+            gxi = gain[[2, 3]] - gxy  # inverse
+            j, k = ((gxy % 1. < g) & (gxy > 1.)).T
+            l, m = ((gxi % 1. < g) & (gxi > 1.)).T
+            j = torch.stack((torch.ones_like(j), j, k, l, m))
+            t = t.repeat((5, 1, 1))[j]
+            offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
+        else:
+            t = targets[0]
+            offsets = 0
+
+        # Define
+        b, c = t[:, :2].long().T  # image, class
+        gxy = t[:, 2:4]  # grid xy
+        gwh = t[:, 4:6]  # grid wh
+        gij = (gxy - offsets).long()
+        gi, gj = gij.T  # grid xy indices
+
+        # Append
+        a = t[:, 6].long()  # anchor indices
+        indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1)))  # image, anchor, grid indices
+        tbox.append(torch.cat((gxy - gij, gwh), 1))  # box
+        anch.append(anchors[a])  # anchors
+        tcls.append(c)  # class
+
+    return tcls, tbox, indices, anch

yolov5/utils/metrics.py

@@ -0,0 +1,200 @@
+# Model validation metrics
+
+from pathlib import Path
+
+import matplotlib.pyplot as plt
+import numpy as np
+import torch
+
+from . import general
+
+
+def fitness(x):
+    # Model fitness as a weighted combination of metrics
+    w = [0.0, 0.0, 0.1, 0.9]  # weights for [P, R, mAP@0.5, mAP@0.5:0.95]
+    return (x[:, :4] * w).sum(1)
+
+
+def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='precision-recall_curve.png', names=[]):
+    """ Compute the average precision, given the recall and precision curves.
+    Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
+    # Arguments
+        tp:  True positives (nparray, nx1 or nx10).
+        conf:  Objectness value from 0-1 (nparray).
+        pred_cls:  Predicted object classes (nparray).
+        target_cls:  True object classes (nparray).
+        plot:  Plot precision-recall curve at mAP@0.5
+        save_dir:  Plot save directory
+    # Returns
+        The average precision as computed in py-faster-rcnn.
+    """
+
+    # Sort by objectness
+    i = np.argsort(-conf)
+    tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
+
+    # Find unique classes
+    unique_classes = np.unique(target_cls)
+
+    # Create Precision-Recall curve and compute AP for each class
+    px, py = np.linspace(0, 1, 1000), []  # for plotting
+    pr_score = 0.1  # score to evaluate P and R https://github.com/ultralytics/yolov3/issues/898
+    s = [unique_classes.shape[0], tp.shape[1]]  # number class, number iou thresholds (i.e. 10 for mAP0.5...0.95)
+    ap, p, r = np.zeros(s), np.zeros(s), np.zeros(s)
+    for ci, c in enumerate(unique_classes):
+        i = pred_cls == c
+        n_l = (target_cls == c).sum()  # number of labels
+        n_p = i.sum()  # number of predictions
+
+        if n_p == 0 or n_l == 0:
+            continue
+        else:
+            # Accumulate FPs and TPs
+            fpc = (1 - tp[i]).cumsum(0)
+            tpc = tp[i].cumsum(0)
+
+            # Recall
+            recall = tpc / (n_l + 1e-16)  # recall curve
+            r[ci] = np.interp(-pr_score, -conf[i], recall[:, 0])  # r at pr_score, negative x, xp because xp decreases
+
+            # Precision
+            precision = tpc / (tpc + fpc)  # precision curve
+            p[ci] = np.interp(-pr_score, -conf[i], precision[:, 0])  # p at pr_score
+
+            # AP from recall-precision curve
+            for j in range(tp.shape[1]):
+                ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j])
+                if plot and (j == 0):
+                    py.append(np.interp(px, mrec, mpre))  # precision at mAP@0.5
+
+    # Compute F1 score (harmonic mean of precision and recall)
+    f1 = 2 * p * r / (p + r + 1e-16)
+
+    if plot:
+        plot_pr_curve(px, py, ap, save_dir, names)
+
+    return p, r, ap, f1, unique_classes.astype('int32')
+
+
+def compute_ap(recall, precision):
+    """ Compute the average precision, given the recall and precision curves
+    # Arguments
+        recall:    The recall curve (list)
+        precision: The precision curve (list)
+    # Returns
+        Average precision, precision curve, recall curve
+    """
+
+    # Append sentinel values to beginning and end
+    mrec = np.concatenate(([0.], recall, [recall[-1] + 0.01]))
+    mpre = np.concatenate(([1.], precision, [0.]))
+
+    # Compute the precision envelope
+    mpre = np.flip(np.maximum.accumulate(np.flip(mpre)))
+
+    # Integrate area under curve
+    method = 'interp'  # methods: 'continuous', 'interp'
+    if method == 'interp':
+        x = np.linspace(0, 1, 101)  # 101-point interp (COCO)
+        ap = np.trapz(np.interp(x, mrec, mpre), x)  # integrate
+    else:  # 'continuous'
+        i = np.where(mrec[1:] != mrec[:-1])[0]  # points where x axis (recall) changes
+        ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])  # area under curve
+
+    return ap, mpre, mrec
+
+
+class ConfusionMatrix:
+    # Updated version of https://github.com/kaanakan/object_detection_confusion_matrix
+    def __init__(self, nc, conf=0.25, iou_thres=0.45):
+        self.matrix = np.zeros((nc + 1, nc + 1))
+        self.nc = nc  # number of classes
+        self.conf = conf
+        self.iou_thres = iou_thres
+
+    def process_batch(self, detections, labels):
+        """
+        Return intersection-over-union (Jaccard index) of boxes.
+        Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
+        Arguments:
+            detections (Array[N, 6]), x1, y1, x2, y2, conf, class
+            labels (Array[M, 5]), class, x1, y1, x2, y2
+        Returns:
+            None, updates confusion matrix accordingly
+        """
+        detections = detections[detections[:, 4] > self.conf]
+        gt_classes = labels[:, 0].int()
+        detection_classes = detections[:, 5].int()
+        iou = general.box_iou(labels[:, 1:], detections[:, :4])
+
+        x = torch.where(iou > self.iou_thres)
+        if x[0].shape[0]:
+            matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()
+            if x[0].shape[0] > 1:
+                matches = matches[matches[:, 2].argsort()[::-1]]
+                matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
+                matches = matches[matches[:, 2].argsort()[::-1]]
+                matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
+        else:
+            matches = np.zeros((0, 3))
+
+        n = matches.shape[0] > 0
+        m0, m1, _ = matches.transpose().astype(np.int16)
+        for i, gc in enumerate(gt_classes):
+            j = m0 == i
+            if n and sum(j) == 1:
+                self.matrix[gc, detection_classes[m1[j]]] += 1  # correct
+            else:
+                self.matrix[gc, self.nc] += 1  # background FP
+
+        if n:
+            for i, dc in enumerate(detection_classes):
+                if not any(m1 == i):
+                    self.matrix[self.nc, dc] += 1  # background FN
+
+    def matrix(self):
+        return self.matrix
+
+    def plot(self, save_dir='', names=()):
+        try:
+            import seaborn as sn
+
+            array = self.matrix / (self.matrix.sum(0).reshape(1, self.nc + 1) + 1E-6)  # normalize
+            array[array < 0.005] = np.nan  # don't annotate (would appear as 0.00)
+
+            fig = plt.figure(figsize=(12, 9), tight_layout=True)
+            sn.set(font_scale=1.0 if self.nc < 50 else 0.8)  # for label size
+            labels = (0 < len(names) < 99) and len(names) == self.nc  # apply names to ticklabels
+            sn.heatmap(array, annot=self.nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True,
+                       xticklabels=names + ['background FN'] if labels else "auto",
+                       yticklabels=names + ['background FP'] if labels else "auto").set_facecolor((1, 1, 1))
+            fig.axes[0].set_xlabel('True')
+            fig.axes[0].set_ylabel('Predicted')
+            fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250)
+        except Exception as e:
+            pass
+
+    def print(self):
+        for i in range(self.nc + 1):
+            print(' '.join(map(str, self.matrix[i])))
+
+
+# Plots ----------------------------------------------------------------------------------------------------------------
+
+def plot_pr_curve(px, py, ap, save_dir='.', names=()):
+    fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
+    py = np.stack(py, axis=1)
+
+    if 0 < len(names) < 21:  # show mAP in legend if < 10 classes
+        for i, y in enumerate(py.T):
+            ax.plot(px, y, linewidth=1, label=f'{names[i]} %.3f' % ap[i, 0])  # plot(recall, precision)
+    else:
+        ax.plot(px, py, linewidth=1, color='grey')  # plot(recall, precision)
+
+    ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean())
+    ax.set_xlabel('Recall')
+    ax.set_ylabel('Precision')
+    ax.set_xlim(0, 1)
+    ax.set_ylim(0, 1)
+    plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
+    fig.savefig(Path(save_dir) / 'precision_recall_curve.png', dpi=250)

yolov5/utils/plots.py

@@ -0,0 +1,412 @@
+# Plotting utils
+
+import glob
+import math
+import os
+import random
+from copy import copy
+from pathlib import Path
+
+import cv2
+import matplotlib
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import seaborn as sns
+import torch
+import yaml
+from PIL import Image, ImageDraw
+from scipy.signal import butter, filtfilt
+
+from utils.general import xywh2xyxy, xyxy2xywh
+from utils.metrics import fitness
+
+# Settings
+matplotlib.rc('font', **{'size': 11})
+matplotlib.use('Agg')  # for writing to files only
+
+
+def color_list():
+    # Return first 10 plt colors as (r,g,b) https://stackoverflow.com/questions/51350872/python-from-color-name-to-rgb
+    def hex2rgb(h):
+        return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4))
+
+    return [hex2rgb(h) for h in plt.rcParams['axes.prop_cycle'].by_key()['color']]
+
+
+def hist2d(x, y, n=100):
+    # 2d histogram used in labels.png and evolve.png
+    xedges, yedges = np.linspace(x.min(), x.max(), n), np.linspace(y.min(), y.max(), n)
+    hist, xedges, yedges = np.histogram2d(x, y, (xedges, yedges))
+    xidx = np.clip(np.digitize(x, xedges) - 1, 0, hist.shape[0] - 1)
+    yidx = np.clip(np.digitize(y, yedges) - 1, 0, hist.shape[1] - 1)
+    return np.log(hist[xidx, yidx])
+
+
+def butter_lowpass_filtfilt(data, cutoff=1500, fs=50000, order=5):
+    # https://stackoverflow.com/questions/28536191/how-to-filter-smooth-with-scipy-numpy
+    def butter_lowpass(cutoff, fs, order):
+        nyq = 0.5 * fs
+        normal_cutoff = cutoff / nyq
+        return butter(order, normal_cutoff, btype='low', analog=False)
+
+    b, a = butter_lowpass(cutoff, fs, order=order)
+    return filtfilt(b, a, data)  # forward-backward filter
+
+
+def plot_one_box(x, img, color=None, label=None, line_thickness=None):
+    # Plots one bounding box on image img
+    tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1  # line/font thickness
+    color = color or [random.randint(0, 255) for _ in range(3)]
+    c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
+    cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
+    if label:
+        tf = max(tl - 1, 1)  # font thickness
+        t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
+        c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
+        cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA)  # filled
+        cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)
+
+
+def plot_wh_methods():  # from utils.plots import *; plot_wh_methods()
+    # Compares the two methods for width-height anchor multiplication
+    # https://github.com/ultralytics/yolov3/issues/168
+    x = np.arange(-4.0, 4.0, .1)
+    ya = np.exp(x)
+    yb = torch.sigmoid(torch.from_numpy(x)).numpy() * 2
+
+    fig = plt.figure(figsize=(6, 3), tight_layout=True)
+    plt.plot(x, ya, '.-', label='YOLOv3')
+    plt.plot(x, yb ** 2, '.-', label='YOLOv5 ^2')
+    plt.plot(x, yb ** 1.6, '.-', label='YOLOv5 ^1.6')
+    plt.xlim(left=-4, right=4)
+    plt.ylim(bottom=0, top=6)
+    plt.xlabel('input')
+    plt.ylabel('output')
+    plt.grid()
+    plt.legend()
+    fig.savefig('comparison.png', dpi=200)
+
+
+def output_to_target(output):
+    # Convert model output to target format [batch_id, class_id, x, y, w, h, conf]
+    targets = []
+    for i, o in enumerate(output):
+        for *box, conf, cls in o.cpu().numpy():
+            targets.append([i, cls, *list(*xyxy2xywh(np.array(box)[None])), conf])
+    return np.array(targets)
+
+
+def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max_size=640, max_subplots=16):
+    # Plot image grid with labels
+
+    if isinstance(images, torch.Tensor):
+        images = images.cpu().float().numpy()
+    if isinstance(targets, torch.Tensor):
+        targets = targets.cpu().numpy()
+
+    # un-normalise
+    if np.max(images[0]) <= 1:
+        images *= 255
+
+    tl = 3  # line thickness
+    tf = max(tl - 1, 1)  # font thickness
+    bs, _, h, w = images.shape  # batch size, _, height, width
+    bs = min(bs, max_subplots)  # limit plot images
+    ns = np.ceil(bs ** 0.5)  # number of subplots (square)
+
+    # Check if we should resize
+    scale_factor = max_size / max(h, w)
+    if scale_factor < 1:
+        h = math.ceil(scale_factor * h)
+        w = math.ceil(scale_factor * w)
+
+    colors = color_list()  # list of colors
+    mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8)  # init
+    for i, img in enumerate(images):
+        if i == max_subplots:  # if last batch has fewer images than we expect
+            break
+
+        block_x = int(w * (i // ns))
+        block_y = int(h * (i % ns))
+
+        img = img.transpose(1, 2, 0)
+        if scale_factor < 1:
+            img = cv2.resize(img, (w, h))
+
+        mosaic[block_y:block_y + h, block_x:block_x + w, :] = img
+        if len(targets) > 0:
+            image_targets = targets[targets[:, 0] == i]
+            boxes = xywh2xyxy(image_targets[:, 2:6]).T
+            classes = image_targets[:, 1].astype('int')
+            labels = image_targets.shape[1] == 6  # labels if no conf column
+            conf = None if labels else image_targets[:, 6]  # check for confidence presence (label vs pred)
+
+            if boxes.shape[1]:
+                if boxes.max() <= 1.01:  # if normalized with tolerance 0.01
+                    boxes[[0, 2]] *= w  # scale to pixels
+                    boxes[[1, 3]] *= h
+                elif scale_factor < 1:  # absolute coords need scale if image scales
+                    boxes *= scale_factor
+            boxes[[0, 2]] += block_x
+            boxes[[1, 3]] += block_y
+            for j, box in enumerate(boxes.T):
+                cls = int(classes[j])
+                color = colors[cls % len(colors)]
+                cls = names[cls] if names else cls
+                if labels or conf[j] > 0.25:  # 0.25 conf thresh
+                    label = '%s' % cls if labels else '%s %.1f' % (cls, conf[j])
+                    plot_one_box(box, mosaic, label=label, color=color, line_thickness=tl)
+
+        # Draw image filename labels
+        if paths:
+            label = Path(paths[i]).name[:40]  # trim to 40 char
+            t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
+            cv2.putText(mosaic, label, (block_x + 5, block_y + t_size[1] + 5), 0, tl / 3, [220, 220, 220], thickness=tf,
+                        lineType=cv2.LINE_AA)
+
+        # Image border
+        cv2.rectangle(mosaic, (block_x, block_y), (block_x + w, block_y + h), (255, 255, 255), thickness=3)
+
+    if fname:
+        r = min(1280. / max(h, w) / ns, 1.0)  # ratio to limit image size
+        mosaic = cv2.resize(mosaic, (int(ns * w * r), int(ns * h * r)), interpolation=cv2.INTER_AREA)
+        # cv2.imwrite(fname, cv2.cvtColor(mosaic, cv2.COLOR_BGR2RGB))  # cv2 save
+        Image.fromarray(mosaic).save(fname)  # PIL save
+    return mosaic
+
+
+def plot_lr_scheduler(optimizer, scheduler, epochs=300, save_dir=''):
+    # Plot LR simulating training for full epochs
+    optimizer, scheduler = copy(optimizer), copy(scheduler)  # do not modify originals
+    y = []
+    for _ in range(epochs):
+        scheduler.step()
+        y.append(optimizer.param_groups[0]['lr'])
+    plt.plot(y, '.-', label='LR')
+    plt.xlabel('epoch')
+    plt.ylabel('LR')
+    plt.grid()
+    plt.xlim(0, epochs)
+    plt.ylim(0)
+    plt.savefig(Path(save_dir) / 'LR.png', dpi=200)
+
+
+def plot_test_txt():  # from utils.plots import *; plot_test()
+    # Plot test.txt histograms
+    x = np.loadtxt('test.txt', dtype=np.float32)
+    box = xyxy2xywh(x[:, :4])
+    cx, cy = box[:, 0], box[:, 1]
+
+    fig, ax = plt.subplots(1, 1, figsize=(6, 6), tight_layout=True)
+    ax.hist2d(cx, cy, bins=600, cmax=10, cmin=0)
+    ax.set_aspect('equal')
+    plt.savefig('hist2d.png', dpi=300)
+
+    fig, ax = plt.subplots(1, 2, figsize=(12, 6), tight_layout=True)
+    ax[0].hist(cx, bins=600)
+    ax[1].hist(cy, bins=600)
+    plt.savefig('hist1d.png', dpi=200)
+
+
+def plot_targets_txt():  # from utils.plots import *; plot_targets_txt()
+    # Plot targets.txt histograms
+    x = np.loadtxt('targets.txt', dtype=np.float32).T
+    s = ['x targets', 'y targets', 'width targets', 'height targets']
+    fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)
+    ax = ax.ravel()
+    for i in range(4):
+        ax[i].hist(x[i], bins=100, label='%.3g +/- %.3g' % (x[i].mean(), x[i].std()))
+        ax[i].legend()
+        ax[i].set_title(s[i])
+    plt.savefig('targets.jpg', dpi=200)
+
+
+def plot_study_txt(path='', x=None):  # from utils.plots import *; plot_study_txt()
+    # Plot study.txt generated by test.py
+    fig, ax = plt.subplots(2, 4, figsize=(10, 6), tight_layout=True)
+    ax = ax.ravel()
+
+    fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True)
+    for f in [Path(path) / f'study_coco_{x}.txt' for x in ['yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']]:
+        y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T
+        x = np.arange(y.shape[1]) if x is None else np.array(x)
+        s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_inference (ms/img)', 't_NMS (ms/img)', 't_total (ms/img)']
+        for i in range(7):
+            ax[i].plot(x, y[i], '.-', linewidth=2, markersize=8)
+            ax[i].set_title(s[i])
+
+        j = y[3].argmax() + 1
+        ax2.plot(y[6, :j], y[3, :j] * 1E2, '.-', linewidth=2, markersize=8,
+                 label=f.stem.replace('study_coco_', '').replace('yolo', 'YOLO'))
+
+    ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5],
+             'k.-', linewidth=2, markersize=8, alpha=.25, label='EfficientDet')
+
+    ax2.grid()
+    ax2.set_xlim(0, 30)
+    ax2.set_ylim(28, 50)
+    ax2.set_yticks(np.arange(30, 55, 5))
+    ax2.set_xlabel('GPU Speed (ms/img)')
+    ax2.set_ylabel('COCO AP val')
+    ax2.legend(loc='lower right')
+    plt.savefig('test_study.png', dpi=300)
+
+
+def plot_labels(labels, save_dir=Path(''), loggers=None):
+    # plot dataset labels
+    print('Plotting labels... ')
+    c, b = labels[:, 0], labels[:, 1:].transpose()  # classes, boxes
+    nc = int(c.max() + 1)  # number of classes
+    colors = color_list()
+    x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height'])
+
+    # seaborn correlogram
+    sns.pairplot(x, corner=True, diag_kind='auto', kind='hist', diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9))
+    plt.savefig(save_dir / 'labels_correlogram.jpg', dpi=200)
+    plt.close()
+
+    # matplotlib labels
+    matplotlib.use('svg')  # faster
+    ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel()
+    ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8)
+    ax[0].set_xlabel('classes')
+    sns.histplot(x, x='x', y='y', ax=ax[2], bins=50, pmax=0.9)
+    sns.histplot(x, x='width', y='height', ax=ax[3], bins=50, pmax=0.9)
+
+    # rectangles
+    labels[:, 1:3] = 0.5  # center
+    labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000
+    img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255)
+    for cls, *box in labels[:1000]:
+        ImageDraw.Draw(img).rectangle(box, width=1, outline=colors[int(cls) % 10])  # plot
+    ax[1].imshow(img)
+    ax[1].axis('off')
+
+    for a in [0, 1, 2, 3]:
+        for s in ['top', 'right', 'left', 'bottom']:
+            ax[a].spines[s].set_visible(False)
+
+    plt.savefig(save_dir / 'labels.jpg', dpi=200)
+    matplotlib.use('Agg')
+    plt.close()
+
+    # loggers
+    for k, v in loggers.items() or {}:
+        if k == 'wandb' and v:
+            v.log({"Labels": [v.Image(str(x), caption=x.name) for x in save_dir.glob('*labels*.jpg')]})
+
+
+def plot_evolution(yaml_file='data/hyp.finetune.yaml'):  # from utils.plots import *; plot_evolution()
+    # Plot hyperparameter evolution results in evolve.txt
+    with open(yaml_file) as f:
+        hyp = yaml.load(f, Loader=yaml.FullLoader)
+    x = np.loadtxt('evolve.txt', ndmin=2)
+    f = fitness(x)
+    # weights = (f - f.min()) ** 2  # for weighted results
+    plt.figure(figsize=(10, 12), tight_layout=True)
+    matplotlib.rc('font', **{'size': 8})
+    for i, (k, v) in enumerate(hyp.items()):
+        y = x[:, i + 7]
+        # mu = (y * weights).sum() / weights.sum()  # best weighted result
+        mu = y[f.argmax()]  # best single result
+        plt.subplot(6, 5, i + 1)
+        plt.scatter(y, f, c=hist2d(y, f, 20), cmap='viridis', alpha=.8, edgecolors='none')
+        plt.plot(mu, f.max(), 'k+', markersize=15)
+        plt.title('%s = %.3g' % (k, mu), fontdict={'size': 9})  # limit to 40 characters
+        if i % 5 != 0:
+            plt.yticks([])
+        print('%15s: %.3g' % (k, mu))
+    plt.savefig('evolve.png', dpi=200)
+    print('\nPlot saved as evolve.png')
+
+
+def profile_idetection(start=0, stop=0, labels=(), save_dir=''):
+    # Plot iDetection '*.txt' per-image logs. from utils.plots import *; profile_idetection()
+    ax = plt.subplots(2, 4, figsize=(12, 6), tight_layout=True)[1].ravel()
+    s = ['Images', 'Free Storage (GB)', 'RAM Usage (GB)', 'Battery', 'dt_raw (ms)', 'dt_smooth (ms)', 'real-world FPS']
+    files = list(Path(save_dir).glob('frames*.txt'))
+    for fi, f in enumerate(files):
+        try:
+            results = np.loadtxt(f, ndmin=2).T[:, 90:-30]  # clip first and last rows
+            n = results.shape[1]  # number of rows
+            x = np.arange(start, min(stop, n) if stop else n)
+            results = results[:, x]
+            t = (results[0] - results[0].min())  # set t0=0s
+            results[0] = x
+            for i, a in enumerate(ax):
+                if i < len(results):
+                    label = labels[fi] if len(labels) else f.stem.replace('frames_', '')
+                    a.plot(t, results[i], marker='.', label=label, linewidth=1, markersize=5)
+                    a.set_title(s[i])
+                    a.set_xlabel('time (s)')
+                    # if fi == len(files) - 1:
+                    #     a.set_ylim(bottom=0)
+                    for side in ['top', 'right']:
+                        a.spines[side].set_visible(False)
+                else:
+                    a.remove()
+        except Exception as e:
+            print('Warning: Plotting error for %s; %s' % (f, e))
+
+    ax[1].legend()
+    plt.savefig(Path(save_dir) / 'idetection_profile.png', dpi=200)
+
+
+def plot_results_overlay(start=0, stop=0):  # from utils.plots import *; plot_results_overlay()
+    # Plot training 'results*.txt', overlaying train and val losses
+    s = ['train', 'train', 'train', 'Precision', 'mAP@0.5', 'val', 'val', 'val', 'Recall', 'mAP@0.5:0.95']  # legends
+    t = ['Box', 'Objectness', 'Classification', 'P-R', 'mAP-F1']  # titles
+    for f in sorted(glob.glob('results*.txt') + glob.glob('../../Downloads/results*.txt')):
+        results = np.loadtxt(f, usecols=[2, 3, 4, 8, 9, 12, 13, 14, 10, 11], ndmin=2).T
+        n = results.shape[1]  # number of rows
+        x = range(start, min(stop, n) if stop else n)
+        fig, ax = plt.subplots(1, 5, figsize=(14, 3.5), tight_layout=True)
+        ax = ax.ravel()
+        for i in range(5):
+            for j in [i, i + 5]:
+                y = results[j, x]
+                ax[i].plot(x, y, marker='.', label=s[j])
+                # y_smooth = butter_lowpass_filtfilt(y)
+                # ax[i].plot(x, np.gradient(y_smooth), marker='.', label=s[j])
+
+            ax[i].set_title(t[i])
+            ax[i].legend()
+            ax[i].set_ylabel(f) if i == 0 else None  # add filename
+        fig.savefig(f.replace('.txt', '.png'), dpi=200)
+
+
+def plot_results(start=0, stop=0, bucket='', id=(), labels=(), save_dir=''):
+    # Plot training 'results*.txt'. from utils.plots import *; plot_results(save_dir='runs/train/exp')
+    fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True)
+    ax = ax.ravel()
+    s = ['Box', 'Objectness', 'Classification', 'Precision', 'Recall',
+         'val Box', 'val Objectness', 'val Classification', 'mAP@0.5', 'mAP@0.5:0.95']
+    if bucket:
+        # files = ['https://storage.googleapis.com/%s/results%g.txt' % (bucket, x) for x in id]
+        files = ['results%g.txt' % x for x in id]
+        c = ('gsutil cp ' + '%s ' * len(files) + '.') % tuple('gs://%s/results%g.txt' % (bucket, x) for x in id)
+        os.system(c)
+    else:
+        files = list(Path(save_dir).glob('results*.txt'))
+    assert len(files), 'No results.txt files found in %s, nothing to plot.' % os.path.abspath(save_dir)
+    for fi, f in enumerate(files):
+        try:
+            results = np.loadtxt(f, usecols=[2, 3, 4, 8, 9, 12, 13, 14, 10, 11], ndmin=2).T
+            n = results.shape[1]  # number of rows
+            x = range(start, min(stop, n) if stop else n)
+            for i in range(10):
+                y = results[i, x]
+                if i in [0, 1, 2, 5, 6, 7]:
+                    y[y == 0] = np.nan  # don't show zero loss values
+                    # y /= y[0]  # normalize
+                label = labels[fi] if len(labels) else f.stem
+                ax[i].plot(x, y, marker='.', label=label, linewidth=2, markersize=8)
+                ax[i].set_title(s[i])
+                # if i in [5, 6, 7]:  # share train and val loss y axes
+                #     ax[i].get_shared_y_axes().join(ax[i], ax[i - 5])
+        except Exception as e:
+            print('Warning: Plotting error for %s; %s' % (f, e))
+
+    ax[1].legend()
+    fig.savefig(Path(save_dir) / 'results.png', dpi=200)

yolov5/utils/torch_utils.py

@@ -0,0 +1,285 @@
+# PyTorch utils
+
+import logging
+import math
+import os
+import time
+from contextlib import contextmanager
+from copy import deepcopy
+
+import torch
+import torch.backends.cudnn as cudnn
+import torch.nn as nn
+import torch.nn.functional as F
+import torchvision
+
+try:
+    import thop  # for FLOPS computation
+except ImportError:
+    thop = None
+logger = logging.getLogger(__name__)
+
+
+@contextmanager
+def torch_distributed_zero_first(local_rank: int):
+    """
+    Decorator to make all processes in distributed training wait for each local_master to do something.
+    """
+    if local_rank not in [-1, 0]:
+        torch.distributed.barrier()
+    yield
+    if local_rank == 0:
+        torch.distributed.barrier()
+
+
+def init_torch_seeds(seed=0):
+    # Speed-reproducibility tradeoff https://pytorch.org/docs/stable/notes/randomness.html
+    torch.manual_seed(seed)
+    if seed == 0:  # slower, more reproducible
+        cudnn.benchmark, cudnn.deterministic = False, True
+    else:  # faster, less reproducible
+        cudnn.benchmark, cudnn.deterministic = True, False
+
+
+def select_device(device='', batch_size=None):
+    # device = 'cpu' or '0' or '0,1,2,3'
+    s = f'Using torch {torch.__version__} '  # string
+    cpu = device.lower() == 'cpu'
+    if cpu:
+        os.environ['CUDA_VISIBLE_DEVICES'] = '-1'  # force torch.cuda.is_available() = False
+    elif device:  # non-cpu device requested
+        os.environ['CUDA_VISIBLE_DEVICES'] = device  # set environment variable
+        assert torch.cuda.is_available(), f'CUDA unavailable, invalid device {device} requested'  # check availability
+
+    cuda = torch.cuda.is_available() and not cpu
+    if cuda:
+        n = torch.cuda.device_count()
+        if n > 1 and batch_size:  # check that batch_size is compatible with device_count
+            assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}'
+        space = ' ' * len(s)
+        for i, d in enumerate(device.split(',') if device else range(n)):
+            p = torch.cuda.get_device_properties(i)
+            s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2}MB)\n"  # bytes to MB
+    else:
+        s += 'CPU'
+
+    logger.info(f'{s}\n')  # skip a line
+    return torch.device('cuda:0' if cuda else 'cpu')
+
+
+def time_synchronized():
+    # pytorch-accurate time
+    if torch.cuda.is_available():
+        torch.cuda.synchronize()
+    return time.time()
+
+
+def profile(x, ops, n=100, device=None):
+    # profile a pytorch module or list of modules. Example usage:
+    #     x = torch.randn(16, 3, 640, 640)  # input
+    #     m1 = lambda x: x * torch.sigmoid(x)
+    #     m2 = nn.SiLU()
+    #     profile(x, [m1, m2], n=100)  # profile speed over 100 iterations
+
+    device = device or torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+    x = x.to(device)
+    x.requires_grad = True
+    print(torch.__version__, device.type, torch.cuda.get_device_properties(0) if device.type == 'cuda' else '')
+    print(f"\n{'Params':>12s}{'GFLOPS':>12s}{'forward (ms)':>16s}{'backward (ms)':>16s}{'input':>24s}{'output':>24s}")
+    for m in ops if isinstance(ops, list) else [ops]:
+        m = m.to(device) if hasattr(m, 'to') else m  # device
+        m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m  # type
+        dtf, dtb, t = 0., 0., [0., 0., 0.]  # dt forward, backward
+        try:
+            flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2  # GFLOPS
+        except:
+            flops = 0
+
+        for _ in range(n):
+            t[0] = time_synchronized()
+            y = m(x)
+            t[1] = time_synchronized()
+            try:
+                _ = y.sum().backward()
+                t[2] = time_synchronized()
+            except:  # no backward method
+                t[2] = float('nan')
+            dtf += (t[1] - t[0]) * 1000 / n  # ms per op forward
+            dtb += (t[2] - t[1]) * 1000 / n  # ms per op backward
+
+        s_in = tuple(x.shape) if isinstance(x, torch.Tensor) else 'list'
+        s_out = tuple(y.shape) if isinstance(y, torch.Tensor) else 'list'
+        p = sum(list(x.numel() for x in m.parameters())) if isinstance(m, nn.Module) else 0  # parameters
+        print(f'{p:12.4g}{flops:12.4g}{dtf:16.4g}{dtb:16.4g}{str(s_in):>24s}{str(s_out):>24s}')
+
+
+def is_parallel(model):
+    return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel)
+
+
+def intersect_dicts(da, db, exclude=()):
+    # Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values
+    return {k: v for k, v in da.items() if k in db and not any(x in k for x in exclude) and v.shape == db[k].shape}
+
+
+def initialize_weights(model):
+    for m in model.modules():
+        t = type(m)
+        if t is nn.Conv2d:
+            pass  # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
+        elif t is nn.BatchNorm2d:
+            m.eps = 1e-3
+            m.momentum = 0.03
+        elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6]:
+            m.inplace = True
+
+
+def find_modules(model, mclass=nn.Conv2d):
+    # Finds layer indices matching module class 'mclass'
+    return [i for i, m in enumerate(model.module_list) if isinstance(m, mclass)]
+
+
+def sparsity(model):
+    # Return global model sparsity
+    a, b = 0., 0.
+    for p in model.parameters():
+        a += p.numel()
+        b += (p == 0).sum()
+    return b / a
+
+
+def prune(model, amount=0.3):
+    # Prune model to requested global sparsity
+    import torch.nn.utils.prune as prune
+    print('Pruning model... ', end='')
+    for name, m in model.named_modules():
+        if isinstance(m, nn.Conv2d):
+            prune.l1_unstructured(m, name='weight', amount=amount)  # prune
+            prune.remove(m, 'weight')  # make permanent
+    print(' %.3g global sparsity' % sparsity(model))
+
+
+def fuse_conv_and_bn(conv, bn):
+    # Fuse convolution and batchnorm layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/
+    fusedconv = nn.Conv2d(conv.in_channels,
+                          conv.out_channels,
+                          kernel_size=conv.kernel_size,
+                          stride=conv.stride,
+                          padding=conv.padding,
+                          groups=conv.groups,
+                          bias=True).requires_grad_(False).to(conv.weight.device)
+
+    # prepare filters
+    w_conv = conv.weight.clone().view(conv.out_channels, -1)
+    w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
+    fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.size()))
+
+    # prepare spatial bias
+    b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias
+    b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps))
+    fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn)
+
+    return fusedconv
+
+
+def model_info(model, verbose=False, img_size=640):
+    # Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320]
+    n_p = sum(x.numel() for x in model.parameters())  # number parameters
+    n_g = sum(x.numel() for x in model.parameters() if x.requires_grad)  # number gradients
+    if verbose:
+        print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
+        for i, (name, p) in enumerate(model.named_parameters()):
+            name = name.replace('module_list.', '')
+            print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
+                  (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
+
+    try:  # FLOPS
+        from thop import profile
+        stride = int(model.stride.max()) if hasattr(model, 'stride') else 32
+        img = torch.zeros((1, model.yaml.get('ch', 3), stride, stride), device=next(model.parameters()).device)  # input
+        flops = profile(deepcopy(model), inputs=(img,), verbose=False)[0] / 1E9 * 2  # stride GFLOPS
+        img_size = img_size if isinstance(img_size, list) else [img_size, img_size]  # expand if int/float
+        fs = ', %.1f GFLOPS' % (flops * img_size[0] / stride * img_size[1] / stride)  # 640x640 GFLOPS
+    except (ImportError, Exception):
+        fs = ''
+
+    logger.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}")
+
+
+def load_classifier(name='resnet101', n=2):
+    # Loads a pretrained model reshaped to n-class output
+    model = torchvision.models.__dict__[name](pretrained=True)
+
+    # ResNet model properties
+    # input_size = [3, 224, 224]
+    # input_space = 'RGB'
+    # input_range = [0, 1]
+    # mean = [0.485, 0.456, 0.406]
+    # std = [0.229, 0.224, 0.225]
+
+    # Reshape output to n classes
+    filters = model.fc.weight.shape[1]
+    model.fc.bias = nn.Parameter(torch.zeros(n), requires_grad=True)
+    model.fc.weight = nn.Parameter(torch.zeros(n, filters), requires_grad=True)
+    model.fc.out_features = n
+    return model
+
+
+def scale_img(img, ratio=1.0, same_shape=False):  # img(16,3,256,416), r=ratio
+    # scales img(bs,3,y,x) by ratio
+    if ratio == 1.0:
+        return img
+    else:
+        h, w = img.shape[2:]
+        s = (int(h * ratio), int(w * ratio))  # new size
+        img = F.interpolate(img, size=s, mode='bilinear', align_corners=False)  # resize
+        if not same_shape:  # pad/crop img
+            gs = 32  # (pixels) grid size
+            h, w = [math.ceil(x * ratio / gs) * gs for x in (h, w)]
+        return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447)  # value = imagenet mean
+
+
+def copy_attr(a, b, include=(), exclude=()):
+    # Copy attributes from b to a, options to only include [...] and to exclude [...]
+    for k, v in b.__dict__.items():
+        if (len(include) and k not in include) or k.startswith('_') or k in exclude:
+            continue
+        else:
+            setattr(a, k, v)
+
+
+class ModelEMA:
+    """ Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models
+    Keep a moving average of everything in the model state_dict (parameters and buffers).
+    This is intended to allow functionality like
+    https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage
+    A smoothed version of the weights is necessary for some training schemes to perform well.
+    This class is sensitive where it is initialized in the sequence of model init,
+    GPU assignment and distributed training wrappers.
+    """
+
+    def __init__(self, model, decay=0.9999, updates=0):
+        # Create EMA
+        self.ema = deepcopy(model.module if is_parallel(model) else model).eval()  # FP32 EMA
+        # if next(model.parameters()).device.type != 'cpu':
+        #     self.ema.half()  # FP16 EMA
+        self.updates = updates  # number of EMA updates
+        self.decay = lambda x: decay * (1 - math.exp(-x / 2000))  # decay exponential ramp (to help early epochs)
+        for p in self.ema.parameters():
+            p.requires_grad_(False)
+
+    def update(self, model):
+        # Update EMA parameters
+        with torch.no_grad():
+            self.updates += 1
+            d = self.decay(self.updates)
+
+            msd = model.module.state_dict() if is_parallel(model) else model.state_dict()  # model state_dict
+            for k, v in self.ema.state_dict().items():
+                if v.dtype.is_floating_point:
+                    v *= d
+                    v += (1. - d) * msd[k].detach()
+
+    def update_attr(self, model, include=(), exclude=('process_group', 'reducer')):
+        # Update EMA attributes
+        copy_attr(self.ema, model, include, exclude)

yolov5/weights/download_weights.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+# Download latest models from https://github.com/ultralytics/yolov5/releases
+# Usage:
+#    $ bash weights/download_weights.sh
+
+python - <<EOF
+from utils.google_utils import attempt_download
+
+for x in ['s', 'm', 'l', 'x']:
+    attempt_download(f'yolov5{x}.pt')
+
+EOF