{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":3649,"databundleVersionId":46718,"sourceType":"competition"}],"dockerImageVersionId":31090,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-08-01T23:51:42.586385Z","iopub.execute_input":"2025-08-01T23:51:42.586584Z","iopub.status.idle":"2025-08-01T23:51:44.674020Z","shell.execute_reply.started":"2025-08-01T23:51:42.586566Z","shell.execute_reply":"2025-08-01T23:51:44.673204Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pip install py7zr","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T23:51:56.299057Z","iopub.execute_input":"2025-08-01T23:51:56.299321Z","iopub.status.idle":"2025-08-01T23:52:02.602275Z","shell.execute_reply.started":"2025-08-01T23:51:56.299301Z","shell.execute_reply":"2025-08-01T23:52:02.601442Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torch.nn as nn\nimport torchvision\nimport torchvision.transforms as transforms\nimport torch.nn.functional as F\nfrom torch.utils.data import Dataset, DataLoader\nfrom PIL import Image\nimport os\nimport math\nimport py7zr\nimport random","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T23:52:05.628658Z","iopub.execute_input":"2025-08-01T23:52:05.628934Z","iopub.status.idle":"2025-08-01T23:52:15.683201Z","shell.execute_reply.started":"2025-08-01T23:52:05.628909Z","shell.execute_reply":"2025-08-01T23:52:15.682501Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T23:52:22.422327Z","iopub.execute_input":"2025-08-01T23:52:22.423076Z","iopub.status.idle":"2025-08-01T23:52:22.495349Z","shell.execute_reply.started":"2025-08-01T23:52:22.423049Z","shell.execute_reply":"2025-08-01T23:52:22.494585Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"archive_path = '../input/cifar-10/train.7z'\nextract_folder = '/kaggle/temp'\nwith py7zr.SevenZipFile(archive_path, mode='r') as archive:\n    archive.extractall(path=extract_folder)\n\narchive_path = '../input/cifar-10/test.7z'\nwith py7zr.SevenZipFile(archive_path, mode='r') as archive:\n    archive.extractall(path=extract_folder)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T23:52:25.626761Z","iopub.execute_input":"2025-08-01T23:52:25.627055Z","iopub.status.idle":"2025-08-01T23:55:11.467815Z","shell.execute_reply.started":"2025-08-01T23:52:25.627032Z","shell.execute_reply":"2025-08-01T23:55:11.466860Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Data augmentation and normalization\nclass CIFAR10CustomDataset(Dataset):\n    def __init__(self, img_dir, labels_df=None, transform=None):\n        self.img_dir = img_dir\n        self.labels_df = labels_df\n        self.transform = transform\n        self.ids = sorted([f for f in os.listdir(img_dir) if f.endswith('.png')])\n\n    def __len__(self):\n        return len(self.ids)\n\n    def __getitem__(self, idx):\n        img_id = self.ids[idx]\n        img = Image.open(os.path.join(self.img_dir, img_id)).convert('RGB')\n        if self.transform:\n            img = self.transform(img)\n\n        if self.labels_df is not None:\n            label = int(self.labels_df.loc[self.labels_df['id'] == int(img_id.split('.')[0]), 'label_idx'].values[0])\n            return img, label\n        else:\n            return img, int(img_id.split('.')[0])\n\n\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        h, w = img.size(1), img.size(2)\n        mask = np.ones((h, w), np.float32)\n\n        for n in range(self.n_holes):\n            y = random.randint(0, h)\n            x = random.randint(0, w)\n\n            y1 = np.clip(y - self.length // 2, 0, h)\n            y2 = np.clip(y + self.length // 2, 0, h)\n            x1 = np.clip(x - self.length // 2, 0, w)\n            x2 = np.clip(x + self.length // 2, 0, w)\n\n            mask[y1:y2, x1:x2] = 0.\n\n        mask = torch.from_numpy(mask).expand_as(img)\n        img = img * mask\n        return img\n\n# Transformation function using PyTorch's transforms\ntrain_transform = transforms.Compose([\n    transforms.RandomHorizontalFlip(p=0.5),  \n    transforms.RandomAffine(degrees=15, translate=(0.1, 0.1), scale=(0.9, 1.1)),  \n    transforms.RandomCrop(32, padding=4),  \n    transforms.ToTensor(),\n    transforms.Normalize(mean=(0.4914, 0.4822, 0.4465), std=(0.2023, 0.1994, 0.2010)),\n    CutOut(n_holes=1, length=8), \n])\n\ntest_transform = transforms.Compose([\n    transforms.Resize((32, 32)), \n    transforms.ToTensor(),\n    transforms.Normalize(mean=(0.4914, 0.4822, 0.4465), std=(0.2023, 0.1994, 0.2010)),\n])\ntrain_csv = pd.read_csv('/kaggle/input/cifar-10/trainLabels.csv')\nlabel_names = sorted(train_csv['label'].unique())\nlabel_to_index = {label: idx for idx, label in enumerate(label_names)}\ntrain_csv['label_idx'] = train_csv['label'].map(label_to_index) # qua nhieu buggg ~~\ntrain_dataset = CIFAR10CustomDataset(img_dir='/kaggle/temp/train',labels_df=train_csv, transform=train_transform)\ntest_dataset = CIFAR10CustomDataset(img_dir='/kaggle/temp/test', transform=test_transform)\ntrain_loader = DataLoader(train_dataset, batch_size=128, shuffle=True)\ntest_loader = DataLoader(test_dataset, batch_size=128, shuffle=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T23:55:36.167140Z","iopub.execute_input":"2025-08-01T23:55:36.168135Z","iopub.status.idle":"2025-08-01T23:55:36.681283Z","shell.execute_reply.started":"2025-08-01T23:55:36.168096Z","shell.execute_reply":"2025-08-01T23:55:36.680414Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class Block(nn.Module):\n    def __init__(self, in_channels, out_channels, stride=1, dropout_rate=0.0):\n        super(Block, self).__init__()\n        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)\n        self.bn1 = nn.BatchNorm2d(out_channels)\n        self.relu1 = nn.ReLU(inplace=True)\n        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)\n        self.bn2 = nn.BatchNorm2d(out_channels)\n        self.relu2 = nn.ReLU(inplace=True)\n        self.dropout = nn.Dropout(dropout_rate)\n        self.shortcut = nn.Sequential()\n        if stride != 1 or in_channels != out_channels:\n            self.shortcut = nn.Sequential(\n                nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride, bias=False),\n                nn.BatchNorm2d(out_channels)\n            )\n\n    def forward(self, x):\n        identity = self.shortcut(x)\n\n        out = self.conv1(x)\n        out = self.bn1(out)\n        out = self.relu1(out)\n\n        out = self.conv2(out)\n        out = self.bn2(out)\n        out = self.dropout(out)\n\n        out += identity\n        out = self.relu2(out)\n        return out\n\nclass WRN(nn.Module):\n    def __init__(self, depth, wide, num_classes=10, dropout_rate=0.0):\n        super(WRN, self).__init__()\n        self.in_channels = 16\n        n = (depth - 4) // 6\n        k = wide\n        temp = [16, 16 * k, 32 * k, 64 * k]\n        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1, bias=False)\n        self.block1 = self.wide_block(Block, temp[1], n, stride=1, dropout_rate=dropout_rate)\n        self.block2 = self.wide_block(Block, temp[2], n, stride=2, dropout_rate=dropout_rate)\n        self.block3 = self.wide_block(Block, temp[3], n, stride=2, dropout_rate=dropout_rate)\n        self.bn = nn.BatchNorm2d(temp[3])\n        self.relu = nn.ReLU(inplace=True)\n        self.linear = nn.Linear(temp[3], num_classes)\n\n    def wide_block(self, block, outputs, num_blocks, stride, dropout_rate=0.0):\n        strides = [stride] + [1] * (num_blocks - 1)\n        layers = []\n        for stride in strides:\n            layers.append(block(self.in_channels, outputs, stride, dropout_rate))\n            self.in_channels = outputs\n        return nn.Sequential(*layers)\n\n    def forward(self, x):\n        out = self.conv1(x)\n        out = self.block1(out)\n        out = self.block2(out)\n        out = self.block3(out)\n        out = self.bn(out)\n        out = self.relu(out)\n        out = F.avg_pool2d(out, 8)\n        out = out.view(out.size(0), -1)\n        out = self.linear(out)\n        return out\n\ndef create_wrn(depth=28, wide=10, num_classes=10, dropout_rate=0.3):\n    return WRN(depth, wide, num_classes, dropout_rate)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T23:55:40.650734Z","iopub.execute_input":"2025-08-01T23:55:40.651221Z","iopub.status.idle":"2025-08-01T23:55:40.674001Z","shell.execute_reply.started":"2025-08-01T23:55:40.651198Z","shell.execute_reply":"2025-08-01T23:55:40.673217Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = create_wrn().to(device)\ncriterion = nn.CrossEntropyLoss()\noptimizer = torch.optim.SGD(model.parameters(), lr=0.001, momentum=0.9, weight_decay=1e-4)\nscheduler = torch.optim.lr_scheduler.OneCycleLR(\n    optimizer,\n    max_lr=0.1,\n    epochs=80,\n    steps_per_epoch=len(train_loader),\n    pct_start=0.3,\n    anneal_strategy='cos',\n    div_factor=25.0,\n    final_div_factor=1e4,  # giảm dần mạnh ở cuối\n)\ndef train(epoch):\n    model.train()\n    running_loss = 0.0\n    correct = 0\n    total = 0\n    for batch_idx, (inputs, targets) in enumerate(train_loader):\n        inputs, targets = inputs.to(device), targets.to(device)\n        optimizer.zero_grad()\n        outputs = model(inputs)\n        loss = criterion(outputs, targets)\n        loss.backward()\n        optimizer.step()\n        scheduler.step()\n        running_loss += loss.item()\n        _, predicted = outputs.max(1)\n        total += targets.size(0)\n        correct += predicted.eq(targets).sum().item()\n    print(f\"Epoch {epoch} | Loss: {running_loss/(batch_idx+1):.3f} | Acc: {100.*correct/total:.2f}%\")\n\n\ndef test(model, test_loader):\n    model.eval()\n    result = []\n    with torch.no_grad():\n        for inputs, ids in test_loader:\n            inputs = inputs.to(device)\n            outputs = model(inputs)\n            _, predicted = torch.max(outputs,1)\n            predicted_names = [label_names[idx] for idx in predicted.cpu().numpy()]\n            result += list(zip(ids,predicted_names))\n    submission_df = pd.DataFrame(result, columns=['id', 'label'])\n    submission_df['id'] = submission_df['id'].astype(int)  \n    submission_df = submission_df.sort_values(by='id')  \n    submission_df.to_csv('submission.csv', index=False)\n\nif __name__ == \"__main__\":\n    num_epochs = 80\n    for epoch in range(num_epochs):\n        print(f\"Epoch {epoch+1}/{num_epochs}\")\n        train(epoch)\n    test(model, test_loader)\n    print(\"Predictions saved to submission.csv\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T23:55:43.590677Z","iopub.execute_input":"2025-08-01T23:55:43.591441Z","iopub.status.idle":"2025-08-02T05:41:54.749661Z","shell.execute_reply.started":"2025-08-01T23:55:43.591412Z","shell.execute_reply":"2025-08-02T05:41:54.748423Z"}},"outputs":[],"execution_count":null}]}