Upload 8 files

data_setup.py

@@ -0,0 +1,54 @@
+import os
+import subprocess
+import zipfile
+from pathlib import Path
+from torch.utils.data import DataLoader
+from torchvision.datasets import ImageFolder
+from torchvision.transforms import ToTensor,Compose, Resize,Normalize 
+
+num_workers = os.cpu_count()
+
+def data_installing(ROOT_PATH, DATA_FILE_ID = '1yIhmdZRwcvyWOl92PygSVGSualOxiwjg'):
+    
+    url = f'https://docs.google.com/uc?export=download&id={DATA_FILE_ID}'
+    output_file = 'data.zip'
+    output_path = ROOT_PATH / 'Data' / output_file
+
+    command = ['wget', '--no-check-certificate', url, '-O', output_path]
+
+    result = subprocess.run(command, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+
+    with zipfile.ZipFile(output_path,'r') as zip:
+        zip.extractall(output_path.parent)
+
+    os.remove(output_path)
+    print('Data loaded..')
+
+
+
+def data_loaders(ROOT_PATH,BATCH_SIZE, IMAGES_SIZE,P):
+
+    transform = Compose([
+        Resize(IMAGES_SIZE),
+        ToTensor(),
+        Normalize(mean=[0.485, 0.456, 0.406],
+                            std=[0.229, 0.224, 0.225]),
+    ])
+
+    train_data = ImageFolder(ROOT_PATH / 'Data' / 'Training_data',
+                            transform=transform)
+   
+    test_data = ImageFolder(ROOT_PATH / 'Data' / 'Test_data',
+                            transform=transform)
+
+    train_data_ = DataLoader(train_data,batch_size = BATCH_SIZE, shuffle=True, num_workers=num_workers)
+    test_data_ = DataLoader(test_data, batch_size=BATCH_SIZE,num_workers=num_workers)
+
+    class_names = train_data.classes
+
+
+    return train_data_,test_data_, class_names
+
+
+if __name__=='__main__':
+    data_installing(Path('/home/hamza/Desktop/Study-Notes/Machine Learning/Pytourch/Modular'))

engine.py

@@ -0,0 +1,55 @@
+import torch
+from sklearn.metrics import accuracy_score
+
+
+
+
+def train_step(
+    epoch,
+    model,
+    loss_fn,
+    optimizer,
+    train_data,
+    device):
+
+    train_loss, train_acc = 0,0
+    for batch, (X,y) in enumerate(train_data):
+        X,y = X.to(device), y.to(device)
+        model.train()
+        optimizer.zero_grad()
+
+        y_pred = model(X)
+        loss = loss_fn(y_pred,y)
+        train_loss+= loss
+        train_acc += accuracy_score(torch.softmax(y_pred,dim=1).argmax(axis=1).cpu(),y.cpu())
+
+        loss.backward()
+        optimizer.step()
+
+    train_loss /= len(train_data)
+    train_acc /= len(train_data)
+    print(f'Epoch {epoch} | train_Loss {train_loss:.2f} | train_acc {train_acc:.2f}')
+
+
+def test_step(
+    epoch,
+    model,
+    loss_fn,
+    test_data,
+    device):
+    
+  
+    
+    model.eval()
+    with torch.inference_mode():
+        test_loss, test_acc = 0,0
+        for _, (X,y) in enumerate(test_data):
+            X,y = X.to(device), y.to(device)
+            y_pred = model(X)
+            test_loss += loss_fn(y_pred,y)
+            test_acc += accuracy_score(torch.softmax(y_pred,dim=1).argmax(axis=1).cpu(),y.cpu())
+
+            test_loss /= len(test_data)
+            test_acc /= len(test_data)
+        print(f'Epoch {epoch} | test_loss {test_loss:.2f} | test_acc {test_acc:.2f}')
+    return test_acc

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2750d2c9f962d54f8290829e70ed20a65f21984a20413d40bf2c1597f9b1ef0d
+size 16438794

model_builder.py

@@ -0,0 +1,42 @@
+from torch import nn
+import torchvision
+from torch.nn.modules import Module, Sequential
+
+
+class FullyDensed(Module):
+    def __init__(self,HIDDEN_UNITS):
+        super().__init__()
+
+        # weights = torchvision.models.EfficientNet_V2_S_Weights.DEFAULT
+        # model = torchvision.models.efficientnet_v2_s(weights=weights)
+        
+        # for param in model.features.parameters():
+        #    param.requires_grad = False
+        # model.classifier[1] = nn.Linear(1280,10)
+        
+        
+        weights = torchvision.models.EfficientNet_B0_Weights.DEFAULT
+        model = torchvision.models.efficientnet_b0(weights=weights)
+
+        for param in model.features.parameters():
+            param.requires_grad = False
+        model.classifier[1] = nn.Linear(1280,10)
+
+
+        self.seq = Sequential(
+            # nn.Conv2d(3,HIDDEN_UNITS,3),
+            # nn.Conv2d(HIDDEN_UNITS,HIDDEN_UNITS,3),
+            # nn.ReLU(),
+            # nn.MaxPool2d(2,2),
+            # nn.Conv2d(HIDDEN_UNITS,HIDDEN_UNITS,3),
+            # nn.Conv2d(HIDDEN_UNITS,50,3),
+            # nn.ReLU(),
+            # nn.MaxPool2d(2,2),
+            # nn.Flatten(),
+            # nn.Linear(800,10)
+            model,
+        )
+
+    def forward(self,x):
+        return self.seq(x)
+

requirements.txt

@@ -0,0 +1,145 @@
+absl-py==2.1.0
+aiofiles==23.2.1
+altair==5.3.0
+annotated-types==0.7.0
+anyio==4.4.0
+asttokens @ file:///home/conda/feedstock_root/build_artifacts/asttokens_1698341106958/work
+astunparse==1.6.3
+attrs==23.2.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+comm @ file:///home/conda/feedstock_root/build_artifacts/comm_1710320294760/work
+contourpy==1.2.1
+cycler==0.12.1
+debugpy @ file:///croot/debugpy_1690905042057/work
+decorator @ file:///home/conda/feedstock_root/build_artifacts/decorator_1641555617451/work
+dnspython==2.6.1
+email_validator==2.1.1
+exceptiongroup @ file:///home/conda/feedstock_root/build_artifacts/exceptiongroup_1704921103267/work
+executing @ file:///home/conda/feedstock_root/build_artifacts/executing_1698579936712/work
+fastapi==0.111.0
+fastapi-cli==0.0.4
+ffmpy==0.3.2
+filelock==3.13.1
+flatbuffers==24.3.25
+fonttools==4.51.0
+fsspec==2024.2.0
+gast==0.5.4
+google-pasta==0.2.0
+gradio==4.36.0
+gradio_client==1.0.1
+grpcio==1.63.0
+h11==0.14.0
+h5py==3.11.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.23.3
+idna==3.7
+importlib_metadata @ file:///home/conda/feedstock_root/build_artifacts/importlib-metadata_1710971335535/work
+importlib_resources==6.4.0
+ipykernel @ file:///home/conda/feedstock_root/build_artifacts/ipykernel_1708996548741/work
+ipython @ file:///home/conda/feedstock_root/build_artifacts/ipython_1715263367085/work
+jedi @ file:///home/conda/feedstock_root/build_artifacts/jedi_1696326070614/work
+Jinja2==3.1.3
+joblib==1.4.2
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+jupyter_client @ file:///home/conda/feedstock_root/build_artifacts/jupyter_client_1710255804825/work
+jupyter_core @ file:///home/conda/feedstock_root/build_artifacts/jupyter_core_1710257359434/work
+keras==3.3.3
+kiwisolver==1.4.5
+libclang==18.1.1
+Markdown==3.6
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.0
+matplotlib-inline @ file:///home/conda/feedstock_root/build_artifacts/matplotlib-inline_1713250518406/work
+mdurl==0.1.2
+ml-dtypes==0.3.2
+mpmath==1.3.0
+namex==0.0.8
+nest_asyncio @ file:///home/conda/feedstock_root/build_artifacts/nest-asyncio_1705850609492/work
+networkx==3.2.1
+numpy==1.26.3
+nvidia-cublas-cu11==11.11.3.6
+nvidia-cuda-cupti-cu11==11.8.87
+nvidia-cuda-nvrtc-cu11==11.8.89
+nvidia-cuda-runtime-cu11==11.8.89
+nvidia-cudnn-cu11==8.7.0.84
+nvidia-cufft-cu11==10.9.0.58
+nvidia-curand-cu11==10.3.0.86
+nvidia-cusolver-cu11==11.4.1.48
+nvidia-cusparse-cu11==11.7.5.86
+nvidia-nccl-cu11==2.20.5
+nvidia-nvtx-cu11==11.8.86
+opt-einsum==3.3.0
+optree==0.11.0
+orjson==3.10.3
+packaging @ file:///home/conda/feedstock_root/build_artifacts/packaging_1710075952259/work
+pandas==2.2.2
+parso @ file:///home/conda/feedstock_root/build_artifacts/parso_1712320355065/work
+pexpect @ file:///home/conda/feedstock_root/build_artifacts/pexpect_1706113125309/work
+pickleshare @ file:///home/conda/feedstock_root/build_artifacts/pickleshare_1602536217715/work
+pillow==10.2.0
+platformdirs @ file:///home/conda/feedstock_root/build_artifacts/platformdirs_1713912794367/work
+prompt-toolkit @ file:///home/conda/feedstock_root/build_artifacts/prompt-toolkit_1702399386289/work
+protobuf==4.25.3
+psutil @ file:///home/conda/feedstock_root/build_artifacts/psutil_1705722403006/work
+ptyprocess @ file:///home/conda/feedstock_root/build_artifacts/ptyprocess_1609419310487/work/dist/ptyprocess-0.7.0-py2.py3-none-any.whl
+pure-eval @ file:///home/conda/feedstock_root/build_artifacts/pure_eval_1642875951954/work
+pydantic==2.7.3
+pydantic_core==2.18.4
+pydub==0.25.1
+Pygments @ file:///home/conda/feedstock_root/build_artifacts/pygments_1714846767233/work
+pyparsing==3.1.2
+python-dateutil @ file:///home/conda/feedstock_root/build_artifacts/python-dateutil_1709299778482/work
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+pyzmq @ file:///croot/pyzmq_1705605076900/work
+referencing==0.35.1
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.1
+ruff==0.4.8
+scikit-learn==1.4.2
+scipy==1.13.0
+semantic-version==2.10.0
+shellingham==1.5.4
+six @ file:///home/conda/feedstock_root/build_artifacts/six_1620240208055/work
+sniffio==1.3.1
+stack-data @ file:///home/conda/feedstock_root/build_artifacts/stack_data_1669632077133/work
+starlette==0.37.2
+sympy==1.12
+tensorboard==2.16.2
+tensorboard-data-server==0.7.2
+tensorflow==2.16.1
+tensorflow-io-gcs-filesystem==0.37.0
+termcolor==2.4.0
+threadpoolctl==3.5.0
+tomlkit==0.12.0
+toolz==0.12.1
+torch==2.3.0+cu118
+torch-summary==1.4.5
+torchaudio==2.3.0+cu118
+torchvision==0.18.0+cu118
+tornado @ file:///home/conda/feedstock_root/build_artifacts/tornado_1708363099148/work
+tqdm==4.66.4
+traitlets @ file:///home/conda/feedstock_root/build_artifacts/traitlets_1713535121073/work
+triton==2.3.0
+typer==0.12.3
+typing_extensions @ file:///home/conda/feedstock_root/build_artifacts/typing_extensions_1712329955671/work
+tzdata==2024.1
+ujson==5.10.0
+urllib3==2.2.1
+uvicorn==0.30.1
+uvloop==0.19.0
+watchfiles==0.22.0
+wcwidth @ file:///home/conda/feedstock_root/build_artifacts/wcwidth_1704731205417/work
+websockets==11.0.3
+Werkzeug==3.0.3
+wrapt==1.16.0
+zipp @ file:///home/conda/feedstock_root/build_artifacts/zipp_1695255097490/work

train.py

@@ -0,0 +1,93 @@
+import torch
+import argparse
+from pathlib import Path
+
+from model_builder import FullyDensed
+from engine import test_step, train_step
+from data_setup import data_loaders
+from utils import save_model
+
+
+
+
+
+def model_training(
+        P,
+        EPOCHS,
+        BATCH_SIZE,
+        HIDDEN_UNITS,
+        IMAGES_SIZE,
+        MODEL_NAME,
+        ROOT_PATH
+):
+
+    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+    device = torch.device('cpu')
+
+    train_data, test_data, class_names = data_loaders(ROOT_PATH=ROOT_PATH,BATCH_SIZE=BATCH_SIZE,IMAGES_SIZE=IMAGES_SIZE,P=P)
+
+    
+    model = FullyDensed(HIDDEN_UNITS)
+    model = model.to(device)
+
+    loss_fn = torch.nn.CrossEntropyLoss()
+    optimizer = torch.optim.Adam(model.parameters())
+
+    for epoch in range(EPOCHS):
+        train_step(
+            epoch,
+            model,
+            loss_fn,
+            optimizer,
+            train_data,
+            device
+            )
+
+        acc = test_step(
+            epoch,
+            model,
+            loss_fn,
+            test_data,
+            device
+        )
+
+
+    save_model(model,path = ROOT_PATH ,MODEL_NAME = MODEL_NAME + f'{int(HIDDEN_UNITS)}-units {int(acc*100//1)}%')
+
+
+
+if __name__=='__main__':
+
+    parser = argparse.ArgumentParser(description='Train a model with specified parameters.')
+    
+
+    parser.add_argument('--P', type=int, default=15)
+
+    parser.add_argument('--epochs', type=int, default=3)
+    parser.add_argument('--batch_size', type=int, default=32)
+    parser.add_argument('--hidden_units', type=int, default=30)
+    parser.add_argument('--images_size', type=int, nargs=2, default=[300,300])
+    parser.add_argument('--model_name', type=str, default='Eff NetB0')
+    parser.add_argument('--root_path', type=str, default='/home/hamza/Desktop/Study-Notes/Machine Learning/Pytourch/Modular')
+
+    args = parser.parse_args()
+
+
+    P = args.P
+    EPOCHS = args.epochs
+    BATCH_SIZE = args.batch_size
+    HIDDEN_UNITS = args.hidden_units
+    IMAGES_SIZE = args.images_size
+    MODEL_NAME = args.model_name
+    ROOT_PATH = Path(args.root_path)
+
+
+    model_training(
+        P,
+        EPOCHS,
+        BATCH_SIZE,
+        HIDDEN_UNITS,
+        IMAGES_SIZE,
+        MODEL_NAME,
+        ROOT_PATH
+    )

utils.py

@@ -0,0 +1,9 @@
+import torch
+
+
+def save_model(model,path,MODEL_NAME):
+    MODEL_NAME = MODEL_NAME + '.pth'
+    SAVED_MODEL_PATH = path / 'Models' / MODEL_NAME
+    torch.save(model,f=SAVED_MODEL_PATH)
+
+