{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30919,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-03-24T04:03:32.182992Z","iopub.execute_input":"2025-03-24T04:03:32.183481Z","iopub.status.idle":"2025-03-24T04:03:32.552250Z","shell.execute_reply.started":"2025-03-24T04:03:32.183436Z","shell.execute_reply":"2025-03-24T04:03:32.551270Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os \n\ndata_dir = '/kaggle/input/dogs-vs-cats'\nprint(os.listdir(data_dir))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-24T04:03:32.553331Z","iopub.execute_input":"2025-03-24T04:03:32.553683Z","iopub.status.idle":"2025-03-24T04:03:32.561257Z","shell.execute_reply.started":"2025-03-24T04:03:32.553660Z","shell.execute_reply":"2025-03-24T04:03:32.560395Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!unzip -qq /kaggle/input/dogs-vs-cats/train.zip","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-24T04:03:32.563061Z","iopub.execute_input":"2025-03-24T04:03:32.563468Z","iopub.status.idle":"2025-03-24T04:03:43.718295Z","shell.execute_reply.started":"2025-03-24T04:03:32.563433Z","shell.execute_reply":"2025-03-24T04:03:43.717209Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nfrom PIL import Image\nplt.figure(figsize = (15,15))\n\nimage =  os.listdir('/kaggle/working/train')\n\nfor i in range(36):\n    plt.subplot(6,6,i+1)\n    img = Image.open(os.path.join('/kaggle/working/train',image[i]))\n    plt.imshow(img)\n    plt.axis('off')\n    plt.title(f\"Image {i+1}\")\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-24T04:03:43.719750Z","iopub.execute_input":"2025-03-24T04:03:43.719995Z","iopub.status.idle":"2025-03-24T04:03:47.613600Z","shell.execute_reply.started":"2025-03-24T04:03:43.719972Z","shell.execute_reply":"2025-03-24T04:03:47.612395Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport shutil\nimport pathlib\nfrom torchvision import datasets, transforms\nfrom torch.utils.data import DataLoader\n\n# Define directories\noriginal_dir = pathlib.Path('train')\nnew_base_dir = pathlib.Path('cats_vs_dogs_small')\n\n# Function to create subsets\ndef make_subset(subset_name, start_index, end_index):\n    for category in ('cat', 'dog'):\n        dir = new_base_dir / subset_name / category\n        os.makedirs(dir, exist_ok=True)\n        fnames = [f\"{category}.{i}.jpg\" for i in range(start_index, end_index)]\n        for fname in fnames:\n            shutil.copyfile(src=original_dir / fname, dst=dir / fname)\n\n# Create training, validation, and test sets\nmake_subset(\"train\", start_index=0, end_index=1000)\nmake_subset(\"validation\", start_index=1000, end_index=1500)\nmake_subset(\"test\", start_index=1500, end_index=2500)\n\n# Define transformations for image processing\ntransform = transforms.Compose([\n    transforms.Resize((150, 150)),  # Resize images to 150x150\n    transforms.ToTensor(),          # Convert images to tensors\n    transforms.Normalize([0.5], [0.5])  # Normalize images to [-1,1]\n])\n\n# Load datasets\ntrain_dataset = datasets.ImageFolder(root=new_base_dir / \"train\", transform=transform)\nval_dataset = datasets.ImageFolder(root=new_base_dir / \"validation\", transform=transform)\ntest_dataset = datasets.ImageFolder(root=new_base_dir / \"test\", transform=transform)\n\n# Create DataLoaders\ntrain_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)\nval_loader = DataLoader(val_dataset, batch_size=32, shuffle=False)\ntest_loader = DataLoader(test_dataset, batch_size=32, shuffle=False)\n\n# Check the dataset\nfor images, labels in train_loader:\n    print(f\"Batch shape: {images.shape}, Labels: {labels}\")\n    break  # Only show first batch\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-24T04:03:47.614970Z","iopub.execute_input":"2025-03-24T04:03:47.615433Z","iopub.status.idle":"2025-03-24T04:03:57.830383Z","shell.execute_reply.started":"2025-03-24T04:03:47.615391Z","shell.execute_reply":"2025-03-24T04:03:57.829422Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# import torch\n# import torch.nn as nn\n# import torch.optim as optim\n# import torchvision.models as models\n\n# # Check for GPU\n# device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n\n# # Define CNN Model\n# class CNNModel(nn.Module):\n#     def __init__(self):\n#         super(CNNModel, self).__init__()\n#         self.conv_layers = nn.Sequential(\n#             nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1),\n#             nn.ReLU(),\n#             nn.MaxPool2d(kernel_size=2, stride=2),\n\n#             nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),\n#             nn.ReLU(),\n#             nn.MaxPool2d(kernel_size=2, stride=2),\n\n#             nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),\n#             nn.ReLU(),\n#             nn.MaxPool2d(kernel_size=2, stride=2)\n#         )\n#         self.fc_layers = nn.Sequential(\n#             nn.Flatten(),\n#             nn.Linear(128 * 18 * 18, 512),  # Adjusted for 150x150 input\n#             nn.ReLU(),\n#             nn.Dropout(0.5),\n#             nn.Linear(512, 2)  # Binary classification: Cat vs Dog\n#         )\n\n#     def forward(self, x):\n#         x = self.conv_layers(x)\n#         x = self.fc_layers(x)\n#         return x\n\n# # Initialize model\n# model = CNNModel().to(device)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-24T04:03:57.831496Z","iopub.execute_input":"2025-03-24T04:03:57.832064Z","iopub.status.idle":"2025-03-24T04:03:57.835876Z","shell.execute_reply.started":"2025-03-24T04:03:57.832026Z","shell.execute_reply":"2025-03-24T04:03:57.834954Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torch.nn as nn\nimport torch.optim as optim\nimport torchvision.models as models\n\n# Check for GPU\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n\n# Load pre-trained ResNet18 model\nclass ResNetModel(nn.Module):\n    def __init__(self, num_classes=2):  # Binary classification: Cat vs Dog\n        super(ResNetModel, self).__init__()\n        self.model = models.resnet18(pretrained=True)\n        \n        # Modify the final fully connected layer\n        in_features = self.model.fc.in_features\n        self.model.fc = nn.Linear(in_features, num_classes)\n    \n    def forward(self, x):\n        return self.model(x)\n\n# Initialize model\nmodel = ResNetModel().to(device)\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-24T04:03:57.836946Z","iopub.execute_input":"2025-03-24T04:03:57.837328Z","iopub.status.idle":"2025-03-24T04:03:58.888155Z","shell.execute_reply.started":"2025-03-24T04:03:57.837296Z","shell.execute_reply":"2025-03-24T04:03:58.887119Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Define loss and optimizer\ncriterion = nn.CrossEntropyLoss()\noptimizer = optim.Adam(model.parameters(), lr=0.001)\n\n# Training loop\nnum_epochs = 10  # You can increase this for better results\n\nfor epoch in range(num_epochs):\n    model.train()\n    running_loss = 0.0\n\n    for images, labels in train_loader:\n        images, labels = images.to(device), labels.to(device)\n\n        optimizer.zero_grad()\n        outputs = model(images)\n        loss = criterion(outputs, labels)\n        loss.backward()\n        optimizer.step()\n\n        running_loss += loss.item()\n\n    print(f\"Epoch [{epoch+1}/{num_epochs}], Loss: {running_loss/len(train_loader):.4f}\")\n\nprint(\"Training Finished!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-24T04:03:58.889260Z","iopub.execute_input":"2025-03-24T04:03:58.889525Z","iopub.status.idle":"2025-03-24T04:05:31.178657Z","shell.execute_reply.started":"2025-03-24T04:03:58.889505Z","shell.execute_reply":"2025-03-24T04:05:31.177637Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Function to calculate accuracy\ndef evaluate(loader):\n    model.eval()\n    correct = 0\n    total = 0\n    with torch.no_grad():\n        for images, labels in loader:\n            images, labels = images.to(device), labels.to(device)\n            outputs = model(images)\n            _, predicted = torch.max(outputs, 1)\n            total += labels.size(0)\n            correct += (predicted == labels).sum().item()\n    return 100 * correct / total\n\n# Validate the model\ntrain_acc = evaluate(train_loader)\nval_acc = evaluate(val_loader)\ntest_acc = evaluate(test_loader)\n\nprint(f\"Train Accuracy: {train_acc:.2f}%\")\nprint(f\"Validation Accuracy: {val_acc:.2f}%\")\nprint(f\"Test Accuracy: {test_acc:.2f}%\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-24T04:05:31.180614Z","iopub.execute_input":"2025-03-24T04:05:31.180866Z","iopub.status.idle":"2025-03-24T04:05:48.787196Z","shell.execute_reply.started":"2025-03-24T04:05:31.180844Z","shell.execute_reply":"2025-03-24T04:05:48.786245Z"}},"outputs":[],"execution_count":null}]}