{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[],"dockerImageVersionId":28755,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport 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))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session\n\n# Use the kagglehub client library to attach Kaggle resources like competitions, datasets, and models to your session\n# Learn more about kagglehub: https://github.com/Kaggle/kagglehub/blob/main/README.md\n\nimport kagglehub\n# kagglehub.dataset_download('<owner>/<dataset-slug>')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2026-06-25T08:26:14.160070Z","iopub.execute_input":"2026-06-25T08:26:14.160366Z","iopub.status.idle":"2026-06-25T08:26:16.028570Z","shell.execute_reply.started":"2026-06-25T08:26:14.160342Z","shell.execute_reply":"2026-06-25T08:26:16.027745Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torch.nn as nn\nimport torch.optim as optim\nimport torch.nn.functional as F\nfrom torch.utils.data import DataLoader\nfrom torchvision import datasets, transforms\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom tqdm import tqdm\nimport warnings\nwarnings.filterwarnings('ignore')\n\n# Check for GPU\ndevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\nprint(f\"Using device: {device}\")\n\n# ==========================================\n# 1. LOAD AND VISUALIZE CIFAR-10 DATA\n# ==========================================\n\n# Data transforms (normalization for CIFAR-10)\ntransform = transforms.Compose([\n    transforms.ToTensor(),\n    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))\n])\n\n# Download and load datasets\ntrain_dataset = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)\ntest_dataset = datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)\n\n# DataLoaders\nbatch_size = 64\ntrain_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=2)\ntest_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False, num_workers=2)\n\n# Class names for CIFAR-10\nclasses = ['airplane', 'automobile', 'bird', 'cat', 'deer', \n           'dog', 'frog', 'horse', 'ship', 'truck']\n\n# Visualize a batch of images\ndef visualize_samples(dataset, classes, num_samples=12):\n    fig, axes = plt.subplots(3, 4, figsize=(12, 9))\n    axes = axes.flatten()\n    \n    # Get random indices\n    indices = np.random.choice(len(dataset), num_samples, replace=False)\n    \n    for i, idx in enumerate(indices):\n        img, label = dataset[idx]\n        # Denormalize image for display\n        img = img / 2 + 0.5  # unnormalize\n        npimg = img.numpy()\n        axes[i].imshow(np.transpose(npimg, (1, 2, 0)))\n        axes[i].set_title(classes[label])\n        axes[i].axis('off')\n    \n    plt.suptitle('Sample CIFAR-10 Images', fontsize=16)\n    plt.tight_layout()\n    plt.savefig('cifar10_samples.png')\n    plt.show()\n\nprint(\"Visualizing CIFAR-10 samples...\")\nvisualize_samples(train_dataset, classes)\n\n# ==========================================\n# 2. BUILD A 2-LAYER CNN\n# ==========================================\n\nclass SimpleCNN(nn.Module):\n    def __init__(self, num_classes=10):\n        super(SimpleCNN, self).__init__()\n        \n        # First convolutional layer: 3 input channels (RGB), 32 output channels\n        self.conv1 = nn.Conv2d(in_channels=3, out_channels=32, kernel_size=3, padding=1)\n        self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, padding=1)\n        \n        # Max pooling layer\n        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)\n        \n        # Fully connected layers\n        self.fc1 = nn.Linear(64 * 8 * 8, 128)\n        self.fc2 = nn.Linear(128, num_classes)\n        \n        # Dropout for regularization\n        self.dropout = nn.Dropout(0.2)\n        \n    def forward(self, x):\n        # Convolutional layers with ReLU and pooling\n        x = self.pool(F.relu(self.conv1(x)))  # 32x32 -> 16x16\n        x = self.pool(F.relu(self.conv2(x)))  # 16x16 -> 8x8\n        \n        # Flatten\n        x = x.view(-1, 64 * 8 * 8)\n        \n        # Fully connected layers with ReLU and dropout\n        x = F.relu(self.fc1(x))\n        x = self.dropout(x)\n        x = self.fc2(x)\n        \n        return x\n\n# Initialize the model\nmodel = SimpleCNN(num_classes=10).to(device)\nprint(f\"Model architecture:\\n{model}\")\nprint(f\"Total parameters: {sum(p.numel() for p in model.parameters()):,}\")\n\n# ==========================================\n# 3. TRAINING FOR 10 EPOCHS\n# ==========================================\n\n# Loss function and optimizer\ncriterion = nn.CrossEntropyLoss()\noptimizer = optim.Adam(model.parameters(), lr=0.001)\nscheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', patience=2, factor=0.5)\n\n# Training loop\nnum_epochs = 10\ntrain_losses = []\nval_losses = []\nval_accuracies = []\n\nprint(\"\\n\" + \"=\"*50)\nprint(\"Starting Training for 10 Epochs\")\nprint(\"=\"*50)\n\nfor epoch in range(1, num_epochs + 1):\n    # Training phase\n    model.train()\n    running_loss = 0.0\n    \n    progress_bar = tqdm(train_loader, desc=f'Epoch {epoch}/{num_epochs} [Train]')\n    for batch_idx, (data, targets) in enumerate(progress_bar):\n        data, targets = data.to(device), targets.to(device)\n        \n        # Forward pass\n        outputs = model(data)\n        loss = criterion(outputs, targets)\n        \n        # Backward pass\n        optimizer.zero_grad()\n        loss.backward()\n        optimizer.step()\n        \n        running_loss += loss.item()\n        \n        # Update progress bar\n        progress_bar.set_postfix({'Loss': f'{loss.item():.4f}'})\n    \n    avg_train_loss = running_loss / len(train_loader)\n    train_losses.append(avg_train_loss)\n    \n    # Validation phase\n    model.eval()\n    val_loss = 0.0\n    correct = 0\n    total = 0\n    \n    with torch.no_grad():\n        for data, targets in tqdm(test_loader, desc=f'Epoch {epoch}/{num_epochs} [Val]'):\n            data, targets = data.to(device), targets.to(device)\n            \n            outputs = model(data)\n            loss = criterion(outputs, targets)\n            \n            val_loss += loss.item()\n            _, predicted = outputs.max(1)\n            total += targets.size(0)\n            correct += (predicted == targets).sum().item()\n    \n    avg_val_loss = val_loss / len(test_loader)\n    val_losses.append(avg_val_loss)\n    \n    val_accuracy = 100. * correct / total\n    val_accuracies.append(val_accuracy)\n    \n    # Learning rate scheduling\n    scheduler.step(avg_val_loss)\n    \n    # Print epoch summary\n    print(f\"\\nEpoch {epoch}/{num_epochs}:\")\n    print(f\"  Train Loss: {avg_train_loss:.4f}\")\n    print(f\"  Val Loss: {avg_val_loss:.4f}\")\n    print(f\"  Val Accuracy: {val_accuracy:.2f}%\")\n    print(\"-\"*50)\n\n# ==========================================\n# 4. PLOT TRAINING VS VALIDATION LOSS\n# ==========================================\n\nplt.figure(figsize=(12, 4))\n\nplt.subplot(1, 2, 1)\nplt.plot(train_losses, label='Training Loss', marker='o')\nplt.plot(val_losses, label='Validation Loss', marker='s')\nplt.xlabel('Epoch')\nplt.ylabel('Loss')\nplt.title('Training vs Validation Loss')\nplt.legend()\nplt.grid(True)\n\nplt.subplot(1, 2, 2)\nplt.plot(val_accuracies, label='Validation Accuracy', marker='o', color='green')\nplt.xlabel('Epoch')\nplt.ylabel('Accuracy (%)')\nplt.title('Validation Accuracy')\nplt.legend()\nplt.grid(True)\n\nplt.tight_layout()\nplt.savefig('training_curves.png')\nplt.show()\n\n# ==========================================\n# 5. FINAL TEST ACCURACY\n# ==========================================\n\nmodel.eval()\ncorrect = 0\ntotal = 0\nall_preds = []\nall_targets = []\n\nwith torch.no_grad():\n    for data, targets in test_loader:\n        data, targets = data.to(device), targets.to(device)\n        outputs = model(data)\n        _, predicted = outputs.max(1)\n        total += targets.size(0)\n        correct += (predicted == targets).sum().item()\n        \n        all_preds.extend(predicted.cpu().numpy())\n        all_targets.extend(targets.cpu().numpy())\n\nfinal_accuracy = 100. * correct / total\nprint(f\"\\n{'='*50}\")\nprint(f\"FINAL TEST ACCURACY: {final_accuracy:.2f}%\")\nprint(f\"{'='*50}\")\n\n# ==========================================\n# 6. SHOW 10 SAMPLE PREDICTIONS\n# ==========================================\n\ndef show_predictions(model, test_loader, classes, num_samples=10):\n    model.eval()\n    \n    # Get a batch of test images\n    data_iter = iter(test_loader)\n    images, labels = next(data_iter)\n    images, labels = images[:num_samples].to(device), labels[:num_samples]\n    \n    # Get predictions\n    with torch.no_grad():\n        outputs = model(images)\n        _, preds = outputs.max(1)\n    \n    # Denormalize images for display\n    images = images.cpu()\n    preds = preds.cpu()\n    labels = labels.cpu()\n    \n    # Plot\n    fig, axes = plt.subplots(2, 5, figsize=(15, 6))\n    axes = axes.flatten()\n    \n    for i in range(num_samples):\n        # Denormalize\n        img = images[i] / 2 + 0.5\n        npimg = img.numpy()\n        axes[i].imshow(np.transpose(npimg, (1, 2, 0)))\n        \n        true_label = classes[labels[i]]\n        pred_label = classes[preds[i]]\n        color = 'green' if preds[i] == labels[i] else 'red'\n        \n        axes[i].set_title(f'True: {true_label}\\nPred: {pred_label}', color=color, fontsize=9)\n        axes[i].axis('off')\n    \n    plt.suptitle('Sample Predictions on Test Set', fontsize=14)\n    plt.tight_layout()\n    plt.savefig('sample_predictions.png')\n    plt.show()\n\nprint(\"\\nVisualizing sample predictions...\")\nshow_predictions(model, test_loader, classes)\n\n# ==========================================\n# 7. SAVE MODEL\n# ==========================================\n\ntorch.save({\n    'model_state_dict': model.state_dict(),\n    'optimizer_state_dict': optimizer.state_dict(),\n    'final_accuracy': final_accuracy,\n    'train_losses': train_losses,\n    'val_losses': val_losses,\n    'val_accuracies': val_accuracies,\n}, 'cifar10_cnn_model.pth')\n\nprint(\"\\n✅ Model saved as 'cifar10_cnn_model.pth'\")\n\n# ==========================================\n# 8. FINAL SUMMARY\n# ==========================================\n\nprint(\"\\n\" + \"=\"*50)\nprint(\"EXPERIMENT COMPLETE!\")\nprint(\"=\"*50)\nprint(f\"✓ Final Test Accuracy: {final_accuracy:.2f}%\")\nprint(f\"✓ Best Validation Accuracy: {max(val_accuracies):.2f}%\")\nprint(f\"✓ Total Epochs: {num_epochs}\")\nprint(f\"✓ Model Parameters: {sum(p.numel() for p in model.parameters()):,}\")\nprint(\"\\n📁 Generated Files:\")\nprint(\"   - cifar10_samples.png (data visualization)\")\nprint(\"   - training_curves.png (loss & accuracy plots)\")\nprint(\"   - sample_predictions.png (10 predictions)\")\nprint(\"   - cifar10_cnn_model.pth (saved model)\")\nprint(\"=\"*50)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-06-25T08:26:16.030215Z","iopub.execute_input":"2026-06-25T08:26:16.030895Z","iopub.status.idle":"2026-06-25T08:28:24.799395Z","shell.execute_reply.started":"2026-06-25T08:26:16.030869Z","shell.execute_reply":"2026-06-25T08:28:24.798697Z"}},"outputs":[],"execution_count":null}]}