{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"},"kaggle":{"accelerator":"gpu","dataSources":[],"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import torch\nimport torch.nn as nn\nimport torch.optim as optim\nimport torch.nn.functional as F\nimport torchvision\nimport torchvision.transforms as transforms\n\n# Define the CutOut augmentation\nclass Cutout(object):\n    def __init__(self, n_holes, length):\n        self.n_holes = n_holes\n        self.length = length\n\n    def __call__(self, img):\n        img = img.clone()\n        h = img.size(1)\n        w = img.size(2)\n        for _ in range(self.n_holes):\n            y = torch.randint(0, h, (1,)).item()\n            x = torch.randint(0, w, (1,)).item()\n            y1 = max(0, y - self.length // 2)\n            y2 = min(h, y + self.length // 2)\n            x1 = max(0, x - self.length // 2)\n            x2 = min(w, x + self.length // 2)\n            img[:, y1:y2, x1:x2] = 0\n        return img\n\n# Define the ResNet block\nclass BasicBlock(nn.Module):\n    def __init__(self, in_planes, planes, stride=1):\n        super(BasicBlock, self).__init__()\n        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)\n        self.bn1 = nn.BatchNorm2d(planes)\n        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)\n        self.bn2 = nn.BatchNorm2d(planes)\n\n        self.shortcut = nn.Sequential()\n        if stride != 1 or in_planes != planes:\n            self.shortcut = nn.Sequential(\n                nn.Conv2d(in_planes, planes, kernel_size=1, stride=stride, bias=False),\n                nn.BatchNorm2d(planes)\n            )\n\n    def forward(self, x):\n        out = F.relu(self.bn1(self.conv1(x)))\n        out = self.bn2(self.conv2(out))\n        out += self.shortcut(x)\n        out = F.relu(out)\n        return out\n\n# Define the ResNet model\nclass ResNet(nn.Module):\n    def __init__(self, block, num_blocks, num_classes=10):\n        super(ResNet, self).__init__()\n        self.in_planes = 64\n\n        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)\n        self.bn1 = nn.BatchNorm2d(64)\n        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)\n        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)\n        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)\n        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)\n        self.linear = nn.Linear(512, num_classes)\n\n    def _make_layer(self, block, planes, num_blocks, stride):\n        strides = [stride] + [1] * (num_blocks - 1)\n        layers = []\n        for stride in strides:\n            layers.append(block(self.in_planes, planes, stride))\n            self.in_planes = planes\n        return nn.Sequential(*layers)\n\n    def forward(self, x):\n        out = F.relu(self.bn1(self.conv1(x)))\n        out = self.layer1(out)\n        out = self.layer2(out)\n        out = self.layer3(out)\n        out = self.layer4(out)\n        out = F.avg_pool2d(out, 4)\n        out = out.view(out.size(0), -1)\n        out = self.linear(out)\n        return out\n\ndef ResNet52():\n    return ResNet(BasicBlock, [3, 4, 6, 3])\n\n# Data augmentation and normalization for training\ntransform_train = transforms.Compose([\n    transforms.RandomCrop(32, padding=4),\n    transforms.RandomHorizontalFlip(),\n    Cutout(n_holes=1, length=16),  # Apply CutOut\n    transforms.ToTensor(),\n    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.247, 0.243, 0.261))\n])\n\ntransform_test = transforms.Compose([\n    transforms.ToTensor(),\n    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.247, 0.243, 0.261))\n])\n\n# Load CIFAR10 dataset\ntrainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform_train)\ntrainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True)\n\ntestset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform_test)\ntestloader = torch.utils.data.DataLoader(testset, batch_size=128, shuffle=False)\n\ndevice = 'cuda' if torch.cuda.is_available() else 'cpu'\nnet = ResNet52().to(device)\n\n# Loss function and optimizer\ncriterion = nn.CrossEntropyLoss()\noptimizer = optim.AdamW(net.parameters(), lr=0.001, weight_decay=1e-4)\n\n# Scheduler with warmup and cosine annealing\nclass CosineAnnealingWarmupRestarts(torch.optim.lr_scheduler.CosineAnnealingLR):\n    def __init__(self, optimizer, T_0, T_mult=1, eta_min=0, last_epoch=-1, warmup_steps=0):\n        self.warmup_steps = warmup_steps\n        self.T_0 = T_0\n        self.T_mult = T_mult\n        self.eta_min = eta_min\n        self.last_epoch = last_epoch\n        super(CosineAnnealingWarmupRestarts, self).__init__(optimizer, T_0, eta_min, last_epoch)\n\n    def get_lr(self):\n        if self.last_epoch < self.warmup_steps:\n            return [base_lr * (self.last_epoch / self.warmup_steps) for base_lr in self.base_lrs]\n        else:\n            return super(CosineAnnealingWarmupRestarts, self).get_lr()\n\nscheduler = CosineAnnealingWarmupRestarts(optimizer, T_0=20, warmup_steps=5)\n\n# Training function\ndef train(epoch):\n    print(f'\\nEpoch: {epoch}')\n    net.train()\n    train_loss = 0\n    correct = 0\n    total = 0\n    for batch_idx, (inputs, targets) in enumerate(trainloader):\n        inputs, targets = inputs.to(device), targets.to(device)\n        optimizer.zero_grad()\n        outputs = net(inputs)\n        loss = criterion(outputs, targets)\n        loss.backward()\n        optimizer.step()\n\n        train_loss += loss.item()\n        _, predicted = outputs.max(1)\n        total += targets.size(0)\n        correct += predicted.eq(targets).sum().item()\n\n        print(f'Batch {batch_idx}/{len(trainloader)} | Loss: {train_loss/(batch_idx+1):.3f} | Acc: {100.*correct/total:.3f}% ({correct}/{total})')\n\n# Testing function\ndef test(epoch):\n    net.eval()\n    test_loss = 0\n    correct = 0\n    total = 0\n    with torch.no_grad():\n        for batch_idx, (inputs, targets) in enumerate(testloader):\n            inputs, targets = inputs.to(device), targets.to(device)\n            outputs = net(inputs)\n            loss = criterion(outputs, targets)\n\n            test_loss += loss.item()\n            _, predicted = outputs.max(1)\n            total += targets.size(0)\n            correct += predicted.eq(targets).sum().item()\n\n            print(f'Batch {batch_idx}/{len(testloader)} | Loss: {test_loss/(batch_idx+1):.3f} | Acc: {100.*correct/total:.3f}% ({correct}/{total})')\n\n# Main training loop for 20 epochs\nfor epoch in range(20):  # Changed to 20 epochs\n    train(epoch)\n    test(epoch)\n    scheduler.step()\n    print(\"Successfully Completed Epoch:\", epoch + 1)\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]}]}