code added

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,3 +1,6 @@
-# AI-Tech-WKO-Projekt
+# Flats datasets
+## Struktura
+Surowe pliki ze zdjęciami nie są trzymane w repozytorium.
 
-Repozytorium do projektu z przedmiotu 'Widzenie komputerowe'
+Przy pierwszym użyciu surowe dane należy umieścić w katalogu `images/raw`, które później będą
+preprocesowane przez skrypty i umieszczone odpowiedno w `images/test` i `images/train`.

data/loaders.py

@@ -0,0 +1,117 @@
+import os
+from abc import ABC
+from pathlib import Path
+from typing import Callable
+
+import cv2 as cv
+import numpy as np
+import torch
+from skimage.io import imread
+from sklearn.preprocessing import LabelEncoder
+from torch.utils.data import Dataset, DataLoader
+from torchvision.transforms import transforms
+
+
+def _load_data(input_dir: str, new_size: int | None = None):
+    image_dir = Path(input_dir)
+    categories_name = {}
+    i = 0
+    for file in os.listdir(image_dir):
+        directory = os.path.join(image_dir, file)
+        if os.path.isdir(directory):
+            categories_name[i] = file
+            i += 1
+
+    folders = [directory for directory in image_dir.iterdir() if directory.is_dir()]
+
+    train_img = []
+    categories_count = len(folders)
+    labels = []
+    for directory in folders:
+        count = 0
+        for obj in directory.iterdir():
+            try:
+                img = imread(obj)
+                if new_size is not None:
+                    img = cv.resize(img, (new_size, new_size), interpolation=cv.INTER_AREA)
+                img = img / 255
+                train_img.append(img)
+                labels.append(os.path.basename(os.path.normpath(directory)))
+                count += 1
+            except ValueError:
+                # This can happen when a file is broken, so let's omit it.
+                print(f'Broken file: {obj}')
+    return {
+        "values": np.array(train_img),
+        "categories_count": categories_count,
+        "labels": labels,
+        "categories_name": categories_name
+    }
+
+
+class FlatsDataset(Dataset):
+    def __init__(self, data, device):
+        self.device = device
+        self.x = []
+        for d in data['values']:
+            self.x.append(transforms.ToTensor()(d))
+        self.y = torch.LongTensor(LabelEncoder().fit_transform(data['labels']))
+
+    def __len__(self):
+        return len(self.x)
+
+    def __getitem__(self, ind):
+        return self.x[ind], self.y[ind]
+
+
+class FlatsDatasetLoader(Dataset, ABC):
+    def __init__(
+            self,
+            images_dir: str,
+            resize_to: int or None = None,
+            batch_size: int = 512,
+            device: str = 'cpu',
+            file_loader: Callable[[str, int or None], dict] = _load_data
+    ):
+        self.images_dir = images_dir
+        self.resize_to = resize_to
+        self.batch_size = batch_size
+        self.device = device
+        self.loader = file_loader
+        self.train_loader = None
+        self.test_loader = None
+        self.classes_count = 0
+        self.label_names = {}
+
+    def load(self, verbose: bool = True):
+        test_dir = os.path.join(self.images_dir, 'test')
+        train_dir = os.path.join(self.images_dir, 'train')
+
+        if verbose:
+            print('Loading dataset from files...')
+        test_raw = self.loader(test_dir, self.resize_to)
+        train_raw = self.loader(train_dir, self.resize_to)
+
+        self.classes_count = test_raw['categories_count']
+        self.label_names = test_raw['categories_name']
+        if verbose:
+            print('Done. Creating PyTorch datasets...')
+        train_set = FlatsDataset(train_raw, self.device)
+        test_set = FlatsDataset(test_raw, self.device)
+
+        self.train_loader = DataLoader(train_set, batch_size=self.batch_size, shuffle=True)
+        self.test_loader = DataLoader(test_set, batch_size=self.batch_size, shuffle=False)
+        if verbose:
+            print('Done.')
+
+    def get_train_loader(self) -> DataLoader:
+        return self.train_loader
+
+    def get_test_loader(self) -> DataLoader:
+        return self.test_loader
+
+    def get_label_names(self) -> dict:
+        return self.label_names
+
+    def get_classes_count(self) -> int:
+        return self.classes_count

data/prepare_alpha_dataset.py

@@ -0,0 +1,58 @@
+import os
+import shutil
+from pathlib import Path
+
+
+def mkdir_if_not_exists(path):
+    try:
+        os.mkdir(path)
+    except FileExistsError:
+        pass
+
+
+def bulk_copy(file_names: list[str], input_dir, output):
+    for i, file in enumerate(file_names):
+        shutil.copy(
+            os.path.join(input_dir, file), os.path.join(output, str(i) + '.' + file.split('.')[1])
+        )
+
+
+def split_houzz_dataset(
+        raw_path: str,
+        train_out_folder: str,
+        test_out_folder: str,
+        train_test_ratio: float = 0.8
+):
+    image_dir = Path(raw_path)
+
+    classes = []
+    for maybe_dir in os.listdir(image_dir):
+        class_dir = os.path.join(image_dir, maybe_dir)
+        if os.path.isdir(class_dir):
+            classes.append(maybe_dir)
+
+    print(f'Found {len(classes)} classes')
+    for cls in classes:
+        mkdir_if_not_exists(os.path.join(train_out_folder, str(cls)))
+        mkdir_if_not_exists(os.path.join(test_out_folder, str(cls)))
+
+    raw_folders = [directory for directory in image_dir.iterdir() if directory.is_dir()]
+    for raw_directory, cls in zip(raw_folders, classes):
+        raw_files = os.listdir(raw_directory)
+        print(f'{raw_directory}: {len(raw_files)}')
+        split_point = round(len(raw_files) * train_test_ratio)
+        train_files = raw_files[:split_point]
+        print(f'\tTrain files: {len(train_files)}')
+        test_files = raw_files[split_point + 1:]
+        print(f'\tTest files: {len(test_files)}')
+        print('Copying... ', end='')
+        bulk_copy(test_files, raw_directory, os.path.join(TEST_OUTPUT, str(cls)))
+        bulk_copy(train_files, raw_directory, os.path.join(TRAIN_OUTPUT, str(cls)))
+        print('Done.')
+
+
+if __name__ == '__main__':
+    HOUZZ_DATASET_PATH = 'images/raw/houzz'
+    TRAIN_OUTPUT = 'images/train'
+    TEST_OUTPUT = 'images/test'
+    split_houzz_dataset(HOUZZ_DATASET_PATH, TRAIN_OUTPUT, TEST_OUTPUT)

experiments/inference.py

@@ -0,0 +1,76 @@
+import argparse
+
+import cv2 as cv
+import numpy as np
+import torch
+from torch import nn
+from torch.utils.data import DataLoader
+from torchvision.transforms import transforms
+
+
+def infer(data, network, loss_fn, device_type):
+    x_cpu, y_cpu = data
+    x = x_cpu.to(device_type).float()
+    y = y_cpu.to(device_type).long()
+    output = network(x)
+    loss = loss_fn(output, y)
+    return output, loss
+
+
+def evaluate(
+        network: nn.Module,
+        test_data: DataLoader,
+        loss_fn,
+        device_type: str
+) -> [np.ndarray, np.ndarray, list[float]]:
+    """
+    Test a given model and return true, predicted values and loss
+    """
+    network.eval()
+    preds, losses = np.array([]), []
+    trues = np.array([])
+    with torch.no_grad():
+        for data in test_data:
+            output, loss = infer(data, network, loss_fn, device_type)
+            trues = np.concatenate((trues, data[1].data.numpy()))
+            preds = np.concatenate(
+                (preds, torch.nn.functional.softmax(output, dim=1)
+                 .cpu()
+                 .data
+                 .numpy()
+                 .argmax(axis=1))
+            )
+            losses.append(loss.item())
+    return trues, preds, losses
+
+
+if __name__ == '__main__':
+    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+    parser = argparse.ArgumentParser(description="Load a model and run inference on a source image")
+    parser.add_argument(
+        "-m", "--model", required=True, type=str, help="path to a pickled model to load"
+    )
+    parser.add_argument \
+        ("-i", "--image", required=True, type=str, help="path to an image to load"
+         )
+    args = parser.parse_args()
+    model = torch.load(args.model)
+    image = cv.imread(args.image)
+    image = image / 255
+    processed = transforms.ToTensor()(image).to(device)
+    predicted = model(processed.float().unsqueeze(0))
+    labels = {
+        '0': 'ArtDeco',
+        '1': 'Classic',
+        '2': 'Glamour',
+        '3': 'Industrial',
+        '4': 'Minimalistic',
+        '5': 'Modern',
+        '6': 'Rustic',
+        '7': 'Scandinavian',
+        '8': 'Vintage',
+    }
+    print(labels[str(
+        torch.nn.functional.softmax(predicted, dim=1).cpu().data.numpy().argmax(axis=1)[0]
+    )])

experiments/metrics.py

@@ -0,0 +1,35 @@
+from statistics import mean
+
+import numpy as np
+from sklearn.metrics import precision_recall_fscore_support, accuracy_score
+
+
+class Metrics:
+    def __init__(self):
+        self.loss = []
+        self.accuracy = []
+        self.precision = []
+        self.recall = []
+        self.f_score = []
+
+    def add_new(self, preds: np.ndarray, trues: np.ndarray, losses: list[float]):
+        self.loss.append(mean(losses))
+        precision, recall, f_scr, _ = precision_recall_fscore_support(
+            trues,
+            preds,
+            average='weighted',
+            zero_division=1
+        )
+        self.precision.append(precision)
+        self.recall.append(recall)
+        self.f_score.append(f_scr)
+        self.accuracy.append(accuracy_score(trues, preds))
+
+    def as_dict(self):
+        return {
+            "loss": self.loss,
+            "acc": self.accuracy,
+            "precision": self.precision,
+            "recall": self.recall,
+            "f": self.f_score
+        }

experiments/plots.py

@@ -0,0 +1,107 @@
+from datetime import timedelta
+
+import matplotlib.pyplot as plt
+import numpy as np
+import seaborn as sns
+from torch.utils.data import Dataset
+from torchvision.transforms import ToPILImage
+
+import metrics
+
+
+def plot_metrics(
+        title: str,
+        test_metrics: metrics.Metrics,
+        train_metrics: metrics.Metrics,
+        n_epochs: int,
+        time: int,
+        image_size: int,
+        device: str = 'cpu'
+):
+    """
+    Shows a plot from collected metrics
+    :param title: Plot title
+    :param test_metrics: A dict of keyed metric scores with arrays as values.
+    Each metric should have the same # of items.
+    Keys:
+    - l - losses
+    - a - accuracy scores
+    - p - precision scores
+    - r - recall scores
+    - f - f scores
+    :param train_metrics: A dict of keyed metric scores with arrays as values.
+    See `test_metrics` for details
+    :param n_epochs:
+    :param time: Time taken to train the model in seconds
+    :param image_size: A number corresponding to the size of images used to train the model
+    :param device: What was used to train the model
+    :return:
+    """
+    plt.style.use('classic')
+    sns.set()
+
+    fig, axis = plt.subplot_mosaic([['l', 'l'],
+                                    ['a', 'p'],
+                                    ['r', 'f']],
+                                   constrained_layout=True, figsize=(10, 10))
+    axis['l'].plot(test_metrics.loss)
+    axis['l'].plot(train_metrics.loss)
+    axis['l'].set_yscale('log')
+    axis['l'].set_title("Loss")
+
+    axis['a'].plot(test_metrics.accuracy)
+    axis['a'].plot(train_metrics.accuracy)
+    axis['a'].set_title("Accuracy")
+
+    axis['p'].plot(test_metrics.precision)
+    axis['p'].plot(train_metrics.precision)
+    axis['p'].set_title("Precision")
+
+    axis['r'].plot(test_metrics.recall)
+    axis['r'].plot(train_metrics.recall)
+    axis['r'].set_title("Recall")
+
+    axis['f'].plot(test_metrics.f_score)
+    axis['f'].plot(train_metrics.f_score)
+    axis['f'].set_title("F-score")
+    fig.tight_layout()
+    fig.subplots_adjust(top=0.90, bottom=0.05)
+    fig.suptitle(title, fontsize=24)
+    fig.legend(axis, labels=['test', 'train'], loc="lower center")
+
+    plt.text(0.30, 0.93,
+             f'{device}, {image_size}x{image_size}, {n_epochs} iteracji, czas treningu: '
+             f'{str(timedelta(seconds=time)).split(".", maxsplit=1)[0]}',
+             fontsize=14,
+             transform=plt.gcf().transFigure)
+    plt.show()
+
+
+def show_missclassified(
+        dataset: Dataset,
+        preds: np.ndarray,
+        label_names: dict,
+        count_per_class: int = 5
+):
+    results = {}
+    for i in label_names.keys():
+        results[i] = []
+
+    indexes = np.random.permutation(len(preds))
+    for i in indexes:
+        pred = preds[i]
+        image_tensor, true = dataset[i]
+        if len(results[pred]) < count_per_class and pred != int(true):
+            results[pred].append({
+                "image": ToPILImage()(image_tensor),
+                "actual": int(true)
+            })
+    sns.reset_orig()
+    plt.figure(figsize=[20, 30])
+    for row, (label, images) in enumerate(results.items()):
+        for i, image in enumerate(images):
+            plt.subplot(len(label_names.keys()), count_per_class, row * count_per_class + i + 1)
+            plt.imshow(image["image"], interpolation="bicubic")
+            plt.title(f'{label_names[label]}, expected {label_names[image["actual"]]}')
+            plt.axis('off')
+    plt.show()