feat: ShapeClassifier

.gitignore

@@ -0,0 +1,165 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# 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/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+
+# ignore dataset but not the folder
+data/raw/*
+data/processed/*

Makefile

@@ -0,0 +1,2 @@
+package:
+	pip freeze > requirements.txt

main.py

@@ -0,0 +1,5 @@
+from src.train import train
+
+if __name__ == "__main__":
+    train()
+

requirements.txt

@@ -0,0 +1,64 @@
+aiofiles==23.2.1
+altair==5.1.1
+annotated-types==0.5.0
+anyio==3.7.1
+attrs==23.1.0
+certifi==2022.12.7
+charset-normalizer==2.1.1
+click==8.1.7
+colorama==0.4.6
+contourpy==1.1.1
+cycler==0.12.0
+exceptiongroup==1.1.3
+fastapi==0.103.2
+ffmpy==0.3.1
+filelock==3.9.0
+fonttools==4.43.0
+fsspec==2023.9.2
+gradio==3.45.2
+gradio_client==0.5.3
+h11==0.14.0
+httpcore==0.18.0
+httpx==0.25.0
+huggingface-hub==0.17.3
+idna==3.4
+importlib-resources==6.1.0
+Jinja2==3.1.2
+jsonschema==4.19.1
+jsonschema-specifications==2023.7.1
+kiwisolver==1.4.5
+MarkupSafe==2.1.2
+matplotlib==3.8.0
+mpmath==1.3.0
+networkx==3.0
+numpy==1.24.1
+orjson==3.9.7
+packaging==23.1
+pandas==2.1.1
+Pillow==9.3.0
+pydantic==2.4.2
+pydantic_core==2.10.1
+pydub==0.25.1
+pyparsing==3.1.1
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.30.2
+requests==2.28.1
+rpds-py==0.10.3
+semantic-version==2.10.0
+six==1.16.0
+sniffio==1.3.0
+starlette==0.27.0
+sympy==1.12
+toolz==0.12.0
+torch==2.0.1+cu117
+torchaudio==2.0.2+cu117
+torchvision==0.15.2+cu117
+tqdm==4.66.1
+typing_extensions==4.8.0
+tzdata==2023.3
+urllib3==1.26.13
+uvicorn==0.23.2
+websockets==11.0.3

src/configs/__init__.py

@@ -0,0 +1,17 @@
+import importlib
+import os
+from inspect import isclass
+
+# import all files under configs/
+configs_dir = os.path.dirname(__file__)
+for file in os.listdir(configs_dir):
+    path = os.path.join(configs_dir, file)
+    if not file.startswith("_") and not file.startswith(".") and (file.endswith(".py") or os.path.isdir(path)):
+        config_name = file[: file.find(".py")] if file.endswith(".py") else file
+        module = importlib.import_module("src.configs." + config_name)
+        for attribute_name in dir(module):
+            attribute = getattr(module, attribute_name)
+
+            if isclass(attribute):
+                # Add the class to this package's variables
+                globals()[attribute_name] = attribute

src/configs/model_config.py

@@ -0,0 +1,10 @@
+import torch
+
+class ModelConfig:
+    def __init__(self):
+        self.learning_rate = 0.001
+        self.batch_size = 32
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+        self.epochs = 20
+    def get_config(self):
+        return self

src/data/__init__.py

@@ -0,0 +1,17 @@
+import importlib
+import os
+from inspect import isclass
+
+# import all files under configs/
+configs_dir = os.path.dirname(__file__)
+for file in os.listdir(configs_dir):
+    path = os.path.join(configs_dir, file)
+    if not file.startswith("_") and not file.startswith(".") and (file.endswith(".py") or os.path.isdir(path)):
+        config_name = file[: file.find(".py")] if file.endswith(".py") else file
+        module = importlib.import_module("src.data." + config_name)
+        for attribute_name in dir(module):
+            attribute = getattr(module, attribute_name)
+
+            if isclass(attribute):
+                # Add the class to this package's variables
+                globals()[attribute_name] = attribute

src/data/data_loader.py

@@ -0,0 +1,21 @@
+from .dataset import CustomDataset
+from torch.utils.data import DataLoader
+from src.configs.model_config import ModelConfig
+from .transform import data_transform
+import os
+
+num_classes = 3
+config = ModelConfig().get_config()
+
+train_dataset = CustomDataset(data_folder=os.path.join("data", 'raw'), transform=data_transform)
+
+# # Calculate the split point
+# split_index = int(0.8 * len(dataset))
+
+# # Split the dataset into training and testing
+# train_dataset = dataset[:split_index]
+# test_dataset = dataset[split_index:]
+
+
+train_loader = DataLoader(train_dataset, batch_size=config.batch_size, shuffle=True)
+

src/data/dataset.py

@@ -0,0 +1,35 @@
+from .transform import data_transform
+from torch.utils.data import Dataset
+import os
+from PIL import Image
+
+
+class CustomDataset(Dataset):
+    def __init__(self, data_folder, transform=None):
+        self.data_folder = data_folder
+        self.image_files = os.listdir(data_folder)
+        self.transform = transform
+
+    def __len__(self):
+        return len(self.image_files)
+
+    def __getitem__(self, idx):
+        image_name = self.image_files[idx]
+        label =image_name[:len(image_name)-8]  # Extract the label from the filename
+       
+
+        image_path = os.path.join(self.data_folder, image_name)
+        image = Image.open(image_path).convert("RGB")  # Ensure images are RGB
+
+        if self.transform:
+            image = self.transform(image)
+        # print("label: ", label, image)
+        if label == "circle":
+            label = 0
+        elif label == "square":
+            label = 1
+        elif label == "triangle":
+            label = 2
+
+        return image, label
+    

src/data/transform.py

@@ -0,0 +1,7 @@
+import torchvision.transforms as transforms
+
+data_transform = transforms.Compose([
+    transforms.Resize((128, 128)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # Use appropriate values
+])

src/models/model.py

@@ -0,0 +1,17 @@
+from torch import nn
+import torch.nn.functional as F
+
+class ShapeClassifier(nn.Module):
+    def __init__(self, num_classes):
+        super(ShapeClassifier, self).__init__()
+        self.conv1 = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=3, padding=1)
+        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
+        self.fc1 = nn.Linear(16 * 64 * 64, 128)
+        self.fc2 = nn.Linear(128, num_classes)
+
+    def forward(self, x):
+        x = self.pool(F.relu(self.conv1(x)))
+        x = x.view(-1, 16 * 64 * 64)  # Adjust the dimensions based on your input image size
+        x = F.relu(self.fc1(x))
+        x = self.fc2(x)
+        return x

src/train.py

@@ -0,0 +1,51 @@
+import torch
+import torch.optim as optim
+import torch.nn.functional as F
+from .models.model import ShapeClassifier
+
+from src.configs.model_config import ModelConfig
+from src.data.data_loader import train_loader, num_classes
+
+
+def train():
+    config = ModelConfig().get_config()
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model = ShapeClassifier(num_classes=num_classes).to(device)
+    optimizer = optim.Adam(model.parameters(), lr=config.learning_rate)
+    log_interval = 20
+    for epoch in range(config.epochs):
+        model.train()
+        running_loss = 0.0
+
+        for batch_idx, (inputs, labels) in enumerate(train_loader):
+            inputs, labels = inputs.to(device), labels.to(device)
+            optimizer.zero_grad()
+
+            outputs = model(inputs)
+            loss = F.cross_entropy(outputs, labels)
+            loss.backward()
+            optimizer.step()
+
+            running_loss += loss.item()
+
+            if batch_idx % log_interval == 0:
+                current_loss = running_loss / log_interval
+                print(
+                    f"Epoch [{epoch + 1}/{config.epochs}], Batch [{batch_idx + 1}/{len(train_loader)}], Loss: {current_loss:.4f}")
+                running_loss = 0.0
+
+                # calculate the accuracy on the test set
+
+                with torch.no_grad():
+                    model.eval()
+                    correct = 0
+                    total = 0
+                    for inputs, labels in train_loader:
+                        inputs, labels = inputs.to(device), labels.to(device)
+                        outputs = model(inputs)
+                        predicted = torch.argmax(outputs.data, 1)
+                        total += labels.size(0)
+                        correct += (predicted == labels).sum().item()
+                    print(f"Accuracy of the model on the test images: {100 * correct / total} %")
+                # save the model
+                torch.save(model.state_dict(), "model.pth")

web.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import torch
+import numpy as np
+from PIL import Image
+from torchvision.transforms import functional as F
+from src.models.model import ShapeClassifier  # Import your model class
+from torchvision import transforms
+import os
+from src.data.transform import data_transform
+
+
+def classify_drawing(drawing_image):
+    # return null if no drawing is provided
+    if drawing_image is None:
+        return None
+
+    # Load the trained model
+    num_classes = 3  # Set the number of classes
+    # Initialize your model class
+    model = ShapeClassifier(num_classes=num_classes)
+    model.load_state_dict(torch.load('model.pth'))
+    model.eval()  # Set the model to evaluation mode
+
+    # Convert the drawing to a grayscale image
+    drawing = np.array(drawing_image)
+
+    drawing_tensor = data_transform(Image.fromarray(drawing))
+
+    # save all the drawing to a folder draw with index
+    Image.fromarray(drawing).save(f'draw/{len(os.listdir("draw"))}.png')
+
+    # Perform inference
+    with torch.no_grad():
+        output = model(drawing_tensor)
+
+    shape_classes = ["Circle", "Square", "Triangle"]
+    predicted_class = torch.argmax(output, dim=1).item()
+    predicted_label = shape_classes[predicted_class]
+
+    return predicted_label
+
+
+iface = gr.Interface(
+    fn=classify_drawing,
+    inputs=gr.Image(type="pil"),  # Use Sketchpad as input
+    outputs="text",
+    live=True,
+    capture_session=True,
+)
+iface.launch(server_port=8111)