{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceType":"competition","sourceId":5441,"databundleVersionId":38425}],"dockerImageVersionId":31041,"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":"2026-03-21T15:14:07.258999Z","iopub.execute_input":"2026-03-21T15:14:07.259747Z","iopub.status.idle":"2026-03-21T15:14:07.521973Z","shell.execute_reply.started":"2026-03-21T15:14:07.259701Z","shell.execute_reply":"2026-03-21T15:14:07.521350Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!unzip /kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip\n!unzip /kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-21T15:14:08.182305Z","iopub.execute_input":"2026-03-21T15:14:08.182683Z"},"_kg_hide-input":true,"_kg_hide-output":true,"scrolled":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Standard library\nimport copy\nimport glob\nimport multiprocessing\nimport os\nimport time\nimport zipfile\n\n# Pytorch\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torch.optim as optim\nfrom torch.utils.data import Dataset, DataLoader\nfrom torchvision import models, transforms\n\n# Related third party\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd\nfrom PIL import Image\nfrom skimage import io, transform\nfrom sklearn.model_selection import train_test_split\nfrom tqdm.notebook import tqdm","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def extract_class_from(path):\n    file = path.split('/')[-1]\n    return file.split('.')[0]","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"input_size = 224\nmean = [0.485, 0.456, 0.406]\nstd = [0.229, 0.224, 0.225]\n\nnum_classes = 2 # dog, cat\n\nbatch_size = 32\nnum_epochs = 2\n\n# Flag for feature extracting. When False, we finetune the whole model,\n#   when True we only update the reshaped layer params\nfeature_extract = True\n\nnum_workers = multiprocessing.cpu_count()\n\ndevice = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"all_train_files = glob.glob(os.path.join(\"/kaggle/working/train\", '*.jpg'))\ntrain_list, val_list = train_test_split(all_train_files, random_state=42)\n\nprint(len(train_list))\nprint(len(val_list))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def train_model(model, dataloaders, criterion, optimizer, num_epochs=25):\n    since = time.time()\n\n    history = {'accuracy': [],\n               'val_accuracy': [],\n               'loss': [],\n               'val_loss': []}\n\n    best_model_wts = copy.deepcopy(model.state_dict())\n    best_acc = 0.0\n\n    for epoch in range(num_epochs):\n        print('Epoch {}/{}'.format(epoch, num_epochs - 1))\n        print('-' * 10)\n\n        # Each epoch has a training and validation phase\n        for phase in ['train', 'val']:\n            if phase == 'train':\n                model.train()  # Set model to training mode\n            else:\n                model.eval()   # Set model to evaluate mode\n\n            running_loss = 0.0\n            running_corrects = 0\n\n            # Iterate over data.\n            for inputs, labels in tqdm(dataloaders[phase]):\n                inputs = inputs.to(device)\n                labels = labels.to(device)\n\n                # zero the parameter gradients\n                optimizer.zero_grad()\n\n                # forward\n                # track history if only in train\n                with torch.set_grad_enabled(phase == 'train'):\n                    outputs = model(inputs)\n                    loss = criterion(outputs, labels)\n\n                    _, preds = torch.max(outputs, 1)\n\n                    # backward + optimize only if in training phase\n                    if phase == 'train':\n                        loss.backward()\n                        optimizer.step()\n\n                # statistics\n                running_loss += loss.item() * inputs.size(0)\n                running_corrects += torch.sum(preds == labels.data)\n\n            epoch_loss = running_loss / len(dataloaders[phase].dataset)\n            epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)\n\n            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))\n\n            # deep copy the model\n            if phase == 'val' and epoch_acc > best_acc:\n                best_acc = epoch_acc\n                best_model_wts = copy.deepcopy(model.state_dict())\n\n            if phase == 'train':\n                history['accuracy'].append(epoch_acc.item())\n                history['loss'].append(epoch_loss)\n            else:\n                history['val_accuracy'].append(epoch_acc.item())\n                history['val_loss'].append(epoch_loss) \n\n        print()\n\n    time_elapsed = time.time() - since\n    print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))\n    print('Best val Acc: {:4f}'.format(best_acc))\n\n    # load best model weights\n    model.load_state_dict(best_model_wts)\n    return model, history","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class DogVsCatDataset(Dataset):\n  \n    def __init__(self, file_list, transform=None):\n        self.file_list = file_list\n        self.transform = transform\n    \n    def __len__(self):\n        return len(self.file_list)\n  \n    def __getitem__(self, idx):\n        if torch.is_tensor(idx):\n            idx = idx.tolist()\n       \n        img_name = self.file_list[idx]\n        image = Image.open(img_name)\n        if self.transform:\n            image = self.transform(image)\n    \n        label_category = extract_class_from(img_name)\n        label = 1 if label_category == 'dog' else 0\n    \n        return image, label","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"data_transforms = {\n    'train': transforms.Compose([\n        transforms.RandomResizedCrop(input_size, scale=(0.5, 1.0)),\n        transforms.RandomHorizontalFlip(),\n        transforms.ToTensor(),\n        transforms.Normalize(mean, std)\n    ]),\n    'val': transforms.Compose([\n        transforms.Resize(input_size),\n        transforms.CenterCrop(input_size),\n        transforms.ToTensor(),\n        transforms.Normalize(mean, std)\n    ])\n}","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_datasets = {\n    'train': DogVsCatDataset(train_list,\n                             transform=data_transforms['train']),\n    'val': DogVsCatDataset(val_list,\n                           transform=data_transforms['val'])\n}\n\ndataloaders_dict = {x: DataLoader(image_datasets[x],\n                                  batch_size=batch_size,\n                                  shuffle=True,\n                                  num_workers=num_workers) for x in ['train', 'val']}","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_ft = models.vit_b_16(pretrained=True)\nmodel_ft.heads = nn.Sequential(\n    nn.Linear(768, 4096),\n    nn.ReLU(),\n    nn.Linear(4096, num_classes)\n)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_ft = model_ft.to(device)\n\nparams_to_update = model_ft.parameters()\nprint(\"Params to learn:\")\nif feature_extract:\n    params_to_update = []\n    for name,param in model_ft.named_parameters():\n        if param.requires_grad == True:\n            params_to_update.append(param)\n            print(\"\\t\",name)\nelse:\n    for name,param in model_ft.named_parameters():\n        if param.requires_grad == True:\n            print(\"\\t\",name)\n\n# Observe that all parameters are being optimized\noptimizer_ft = optim.AdamW(params_to_update, lr=1e-5)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Setup the loss fxn\ncriterion = nn.CrossEntropyLoss()\n\n# Train and evaluate\nmodel_ft, hist = train_model(model_ft, dataloaders_dict, criterion, optimizer_ft, num_epochs=num_epochs)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_list = glob.glob(os.path.join(\"/kaggle/working/test\", '*.jpg'))\ntest_data_transform = data_transforms['val']\n\nids = []\nlabels = []\n\nwith torch.no_grad():\n    for test_path in tqdm(test_list):\n        img = Image.open(test_path)\n        img = test_data_transform(img)\n        img = img.unsqueeze(0)\n        img = img.to(device)\n\n        model_ft.eval()\n        outputs = model_ft(img)\n        preds = F.softmax(outputs, dim=1)[:, 1].tolist()\n\n        test_id = extract_class_from(test_path)\n        ids.append(int(test_id))\n        labels.append(preds[0])","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output = pd.DataFrame({'id': ids,\n                       'label': labels})\n\noutput.sort_values(by='id', inplace=True)\noutput.reset_index(drop=True, inplace=True)\n\noutput.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}