Compare commits
1 Commits
NeurNetPro
...
master
Author | SHA1 | Date | |
---|---|---|---|
0c5532ac0d |
@ -3,5 +3,5 @@
|
||||
<component name="Black">
|
||||
<option name="sdkName" value="Python 3.9 (traktor)" />
|
||||
</component>
|
||||
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12" project-jdk-type="Python SDK" />
|
||||
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (traktor)" project-jdk-type="Python SDK" />
|
||||
</project>
|
@ -1,60 +0,0 @@
|
||||
import glob
|
||||
from src.torchvision_resize_dataset import combined_dataset, images_path, classes
|
||||
import src.data_model
|
||||
from torch.optim import Adam
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torch.utils.data import DataLoader
|
||||
|
||||
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
|
||||
train_loader = DataLoader(
|
||||
combined_dataset, #dataset of images
|
||||
batch_size=256, # accuracy
|
||||
shuffle=True # rand order
|
||||
)
|
||||
|
||||
model = src.data_model.DataModel(num_objects=2).to(device)
|
||||
|
||||
#optimizer
|
||||
optimizer = Adam(model.parameters(), lr=0.001, weight_decay=0.0001)
|
||||
#loss function
|
||||
criterion = nn.CrossEntropyLoss()
|
||||
|
||||
num_epochs = 20
|
||||
# train_size = len(glob.glob(images_path+'*.jpg'))
|
||||
train_size = 2000
|
||||
|
||||
go_to_accuracy = 0.0
|
||||
for epoch in range(num_epochs):
|
||||
#training on dataset
|
||||
model.train()
|
||||
train_accuracy = 0.0
|
||||
train_loss = 0.0
|
||||
for i, (images, labels) in enumerate(train_loader):
|
||||
if torch.cuda.is_available():
|
||||
images = torch.Variable(images.cuda())
|
||||
labels = torch.Variable(labels.cuda())
|
||||
# clearing the optimizer gradients
|
||||
optimizer.zero_grad()
|
||||
|
||||
outputs = model(images) # prediction
|
||||
loss = criterion(outputs, labels) #loss calculation
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
train_loss += loss.cpu().data*images.size(0)
|
||||
_, prediction = torch.max(outputs.data, 1)
|
||||
|
||||
train_accuracy += int(torch.sum(prediction == labels.data))
|
||||
|
||||
train_accuracy = train_accuracy/train_size
|
||||
train_loss = train_loss/train_size
|
||||
|
||||
model.eval()
|
||||
|
||||
print('Epoch: '+ str(epoch+1) +' Train Loss: '+ str(int(train_loss)) +' Train Accuracy: '+ str(train_accuracy))
|
||||
|
||||
if train_accuracy > go_to_accuracy:
|
||||
go_to_accuracy= train_accuracy
|
||||
torch.save(model.state_dict(), "best_model.pth")
|
@ -1,146 +0,0 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torchvision.transforms import transforms
|
||||
import numpy as np
|
||||
from torch.autograd import Variable
|
||||
from torchvision.models import squeezenet1_1
|
||||
import torch.functional as F
|
||||
from io import open
|
||||
import os
|
||||
from PIL import Image
|
||||
import pathlib
|
||||
import glob
|
||||
from tkinter import Tk, Label
|
||||
from PIL import Image, ImageTk
|
||||
|
||||
train_path = os.path.abspath('src/train_images')
|
||||
pred_path = os.path.abspath('src/test_images')
|
||||
|
||||
root = pathlib.Path(train_path)
|
||||
classes = sorted([j.name.split('/')[-1] for j in root.iterdir()])
|
||||
|
||||
|
||||
class DataModel(nn.Module):
|
||||
def __init__(self, num_classes):
|
||||
super(DataModel, self).__init__()
|
||||
# input (batch=256, nr of channels rgb=3 , size=244x244)
|
||||
|
||||
# convolution
|
||||
self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=3, stride=1, padding=1)
|
||||
# shape (256, 12, 224x224)
|
||||
|
||||
# batch normalization
|
||||
self.bn1 = nn.BatchNorm2d(num_features=12)
|
||||
# shape (256, 12, 224x224)
|
||||
self.reul1 = nn.ReLU()
|
||||
|
||||
self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
|
||||
# reduce image size by factor 2
|
||||
# pooling window moves by 2 pixels at a time instead of 1
|
||||
# shape (256, 12, 112x112)
|
||||
|
||||
self.conv2 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=3, stride=1, padding=1)
|
||||
self.bn2 = nn.BatchNorm2d(num_features=24)
|
||||
self.reul2 = nn.ReLU()
|
||||
# shape (256, 24, 112x112)
|
||||
|
||||
self.conv3 = nn.Conv2d(in_channels=24, out_channels=48, kernel_size=3, stride=1, padding=1)
|
||||
# shape (256, 48, 112x112)
|
||||
self.bn3 = nn.BatchNorm2d(num_features=48)
|
||||
# shape (256, 48, 112x112)
|
||||
self.reul3 = nn.ReLU()
|
||||
|
||||
# connected layer
|
||||
self.fc = nn.Linear(in_features=48 * 112 * 112, out_features=num_classes)
|
||||
|
||||
def forward(self, input):
|
||||
output = self.conv1(input)
|
||||
output = self.bn1(output)
|
||||
output = self.reul1(output)
|
||||
|
||||
output = self.pool(output)
|
||||
output = self.conv2(output)
|
||||
output = self.bn2(output)
|
||||
output = self.reul2(output)
|
||||
|
||||
output = self.conv3(output)
|
||||
output = self.bn3(output)
|
||||
output = self.reul3(output)
|
||||
|
||||
# output shape matrix (256, 48, 112x112)
|
||||
# print(output.shape)
|
||||
# print(self.fc.weight.shape)
|
||||
|
||||
output = output.view(-1, 48 * 112 * 112)
|
||||
output = self.fc(output)
|
||||
|
||||
return output
|
||||
|
||||
|
||||
script_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
file_path = os.path.join(script_dir, 'best_model.pth')
|
||||
checkpoint = torch.load(file_path)
|
||||
model = DataModel(num_classes=2)
|
||||
model.load_state_dict(checkpoint)
|
||||
model.eval()
|
||||
|
||||
transformer = transforms.Compose([
|
||||
transforms.Resize((224, 224)), # Resize images to (224, 224)
|
||||
transforms.ToTensor(), # Convert images to tensors, 0-255 to 0-1
|
||||
# transforms.RandomHorizontalFlip(), # 0.5 chance to flip the image
|
||||
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
|
||||
])
|
||||
|
||||
|
||||
def prediction(img_path, transformer):
|
||||
image = Image.open(img_path)
|
||||
|
||||
image_tensor = transformer(image).float()
|
||||
|
||||
image_tensor = image_tensor.unsqueeze_(0)
|
||||
|
||||
if torch.cuda.is_available():
|
||||
image_tensor.cuda()
|
||||
|
||||
input = Variable(image_tensor)
|
||||
|
||||
output = model(input)
|
||||
|
||||
index = output.data.numpy().argmax()
|
||||
|
||||
pred = classes[index]
|
||||
|
||||
return pred
|
||||
|
||||
|
||||
def prediction_keys():
|
||||
# funkcja zwracajaca sciezki do kazdego pliku w folderze w postaci listy
|
||||
|
||||
images_path = glob.glob(pred_path + '/*.jpg')
|
||||
|
||||
pred_list = []
|
||||
|
||||
for i in images_path:
|
||||
pred_list.append(i)
|
||||
|
||||
return pred_list
|
||||
|
||||
|
||||
def predict_one(path):
|
||||
# wyswietlanie obrazka po kazdym podniesieniu itemu
|
||||
root = Tk()
|
||||
root.title("Okno z obrazkiem")
|
||||
|
||||
image = Image.open(path)
|
||||
photo = ImageTk.PhotoImage(image)
|
||||
label = Label(root, image = photo)
|
||||
label.pack()
|
||||
|
||||
root.mainloop()
|
||||
|
||||
# uruchamia sie funkcja spr czy obrazek to paczka czy list
|
||||
pred_print = prediction(path, transformer)
|
||||
print('Zdjecie jest: ' + pred_print)
|
||||
return pred_print
|
||||
|
||||
predict_one('src/test_images/1.jpg')
|
@ -1,59 +0,0 @@
|
||||
import torch.nn as nn
|
||||
import torch
|
||||
|
||||
|
||||
class DataModel(nn.Module):
|
||||
def __init__(self, num_objects):
|
||||
super(DataModel, self).__init__()
|
||||
# input (batch=256, nr of channels rgb=3 , size=244x244)
|
||||
|
||||
# convolution
|
||||
self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=3, stride=1, padding=1)
|
||||
# shape (256, 12, 224x224)
|
||||
|
||||
# batch normalization
|
||||
self.bn1 = nn.BatchNorm2d(num_features=12)
|
||||
# shape (256, 12, 224x224)
|
||||
self.reul1 = nn.ReLU()
|
||||
|
||||
self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
|
||||
# reduce image size by factor 2
|
||||
# pooling window moves by 2 pixels at a time instead of 1
|
||||
# shape (256, 12, 112x112)
|
||||
|
||||
self.conv2 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=3, stride=1, padding=1)
|
||||
self.bn2 = nn.BatchNorm2d(num_features=24)
|
||||
self.reul2 = nn.ReLU()
|
||||
# shape (256, 24, 112x112)
|
||||
|
||||
self.conv3 = nn.Conv2d(in_channels=24, out_channels=48, kernel_size=3, stride=1, padding=1)
|
||||
# shape (256, 48, 112x112)
|
||||
self.bn3 = nn.BatchNorm2d(num_features=48)
|
||||
# shape (256, 48, 112x112)
|
||||
self.reul3 = nn.ReLU()
|
||||
|
||||
# connected layer
|
||||
self.fc = nn.Linear(in_features=48 * 112 * 112, out_features=num_objects)
|
||||
|
||||
def forward(self, input):
|
||||
output = self.conv1(input)
|
||||
output = self.bn1(output)
|
||||
output = self.reul1(output)
|
||||
|
||||
output = self.pool(output)
|
||||
output = self.conv2(output)
|
||||
output = self.bn2(output)
|
||||
output = self.reul2(output)
|
||||
|
||||
output = self.conv3(output)
|
||||
output = self.bn3(output)
|
||||
output = self.reul3(output)
|
||||
|
||||
# output shape matrix (256, 48, 112x112)
|
||||
# print(output.shape)
|
||||
# print(self.fc.weight.shape)
|
||||
|
||||
output = output.view(-1, 48 * 112 * 112)
|
||||
output = self.fc(output)
|
||||
|
||||
return output
|
Before Width: | Height: | Size: 31 KiB |
Before Width: | Height: | Size: 17 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 54 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 11 KiB |
Before Width: | Height: | Size: 31 KiB |
Before Width: | Height: | Size: 18 KiB |
Before Width: | Height: | Size: 17 KiB |
@ -1,31 +0,0 @@
|
||||
import glob
|
||||
import pathlib
|
||||
import torchvision.transforms as transforms
|
||||
from torchvision.datasets import ImageFolder
|
||||
from torch.utils.data import ConcatDataset
|
||||
|
||||
# images have to be the same size for the algorithm to work
|
||||
transform = transforms.Compose([
|
||||
transforms.Resize((224, 224)), # Resize images to (224, 224)
|
||||
transforms.ToTensor(), # Convert images to tensors, 0-255 to 0-1
|
||||
# transforms.RandomHorizontalFlip(), # 0.5 chance to flip the image
|
||||
transforms.Normalize([0.5,0.5,0.5], [0.5,0.5,0.5])
|
||||
])
|
||||
|
||||
carrot_path = '/train_images/carrot'
|
||||
potato_path = '/train_images/potato'
|
||||
images_path = '/train_images'
|
||||
|
||||
# # Load images from folders
|
||||
# letter_folder = ImageFolder(letters_path, transform=transform)
|
||||
# package_folder = ImageFolder(package_path, transform=transform)
|
||||
|
||||
# Combine the both datasets into a single dataset
|
||||
#combined_dataset = ConcatDataset([letter_folder, package_folder])
|
||||
combined_dataset = ImageFolder(images_path, transform=transform)
|
||||
|
||||
#image classes
|
||||
path=pathlib.Path(images_path)
|
||||
classes = sorted([i.name.split("/")[-1] for i in path.iterdir()])
|
||||
|
||||
# print(classes)
|
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 38 KiB |
Before Width: | Height: | Size: 12 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 35 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 17 KiB |
Before Width: | Height: | Size: 13 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 31 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 17 KiB |
Before Width: | Height: | Size: 33 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 17 KiB |
Before Width: | Height: | Size: 18 KiB |
Before Width: | Height: | Size: 13 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 32 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 11 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 17 KiB |
Before Width: | Height: | Size: 12 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 23 KiB |
Before Width: | Height: | Size: 19 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 24 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 11 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 17 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 19 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 19 KiB |
Before Width: | Height: | Size: 17 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 9.8 KiB |
Before Width: | Height: | Size: 11 KiB |
Before Width: | Height: | Size: 13 KiB |
Before Width: | Height: | Size: 12 KiB |
Before Width: | Height: | Size: 19 KiB |
Before Width: | Height: | Size: 11 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 13 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 11 KiB |
Before Width: | Height: | Size: 19 KiB |
Before Width: | Height: | Size: 13 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 14 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 11 KiB |
Before Width: | Height: | Size: 17 KiB |
Before Width: | Height: | Size: 11 KiB |
Before Width: | Height: | Size: 15 KiB |
Before Width: | Height: | Size: 18 KiB |
Before Width: | Height: | Size: 40 KiB |
Before Width: | Height: | Size: 11 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 19 KiB |
Before Width: | Height: | Size: 17 KiB |
Before Width: | Height: | Size: 30 KiB |
Before Width: | Height: | Size: 23 KiB |
Before Width: | Height: | Size: 16 KiB |
Before Width: | Height: | Size: 18 KiB |
Before Width: | Height: | Size: 34 KiB |