{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"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":5441,"databundleVersionId":38425,"sourceType":"competition"}],"dockerImageVersionId":30636,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"Kaggle link: https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition","metadata":{}},{"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":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","execution":{"iopub.status.busy":"2024-01-11T19:58:18.354452Z","iopub.execute_input":"2024-01-11T19:58:18.355323Z","iopub.status.idle":"2024-01-11T19:58:18.362362Z","shell.execute_reply.started":"2024-01-11T19:58:18.355286Z","shell.execute_reply":"2024-01-11T19:58:18.361363Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Import everything needed","metadata":{}},{"cell_type":"code","source":"import zipfile\nimport glob\nfrom PIL import Image\nimport matplotlib.pyplot as plt\n\nfrom sklearn.model_selection import train_test_split\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torch.optim as optim\nfrom torch.utils.data import DataLoader, Dataset\nfrom torchvision import datasets, transforms\nnp.random.seed(0)\ntorch.manual_seed(0)\ntorch.cuda.manual_seed(0)","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:18.364128Z","iopub.execute_input":"2024-01-11T19:58:18.365090Z","iopub.status.idle":"2024-01-11T19:58:18.374611Z","shell.execute_reply.started":"2024-01-11T19:58:18.365055Z","shell.execute_reply":"2024-01-11T19:58:18.373764Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Unzip datasets","metadata":{}},{"cell_type":"code","source":"train_dir = 'train'\ntest_dir = 'test'\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip') as train_zip:\n    train_zip.extractall('')\n    \nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip') as test_zip:\n    test_zip.extractall('')\ntrain_list = glob.glob(os.path.join(train_dir,'*.jpg'))\ntest_list = glob.glob(os.path.join(test_dir, '*.jpg'))\nprint(f\"Train Data: {len(train_list)}\")\nprint(f\"Test Data: {len(test_list)}\")","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:18.376343Z","iopub.execute_input":"2024-01-11T19:58:18.376675Z","iopub.status.idle":"2024-01-11T19:58:29.627491Z","shell.execute_reply.started":"2024-01-11T19:58:18.376651Z","shell.execute_reply":"2024-01-11T19:58:29.626457Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels = [path.split('/')[-1].split('.')[0] for path in train_list]","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:29.628796Z","iopub.execute_input":"2024-01-11T19:58:29.629173Z","iopub.status.idle":"2024-01-11T19:58:29.647965Z","shell.execute_reply.started":"2024-01-11T19:58:29.629137Z","shell.execute_reply":"2024-01-11T19:58:29.646972Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Plot random image with their label","metadata":{}},{"cell_type":"code","source":"random_idx = np.random.randint(1, len(train_list), size=9)\nfig, axes = plt.subplots(3, 3, figsize=(16, 12))\n\nfor idx, ax in enumerate(axes.ravel()):\n    img = Image.open(train_list[idx])\n    ax.set_title(labels[idx])\n    ax.imshow(img)","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:29.650446Z","iopub.execute_input":"2024-01-11T19:58:29.650772Z","iopub.status.idle":"2024-01-11T19:58:32.671759Z","shell.execute_reply.started":"2024-01-11T19:58:29.650741Z","shell.execute_reply":"2024-01-11T19:58:32.670684Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Use Sklearn to split the training data","metadata":{}},{"cell_type":"code","source":"train_list, valid_list = train_test_split(train_list, \n                                          test_size=0.2,\n                                          stratify=labels,\n                                          random_state=0)","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:32.672969Z","iopub.execute_input":"2024-01-11T19:58:32.673273Z","iopub.status.idle":"2024-01-11T19:58:32.703483Z","shell.execute_reply.started":"2024-01-11T19:58:32.673248Z","shell.execute_reply":"2024-01-11T19:58:32.702734Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f\"Train Data: {len(train_list)}\")\nprint(f\"Validation Data: {len(valid_list)}\")\nprint(f\"Test Data: {len(test_list)}\")","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:32.704643Z","iopub.execute_input":"2024-01-11T19:58:32.704977Z","iopub.status.idle":"2024-01-11T19:58:32.710130Z","shell.execute_reply.started":"2024-01-11T19:58:32.704951Z","shell.execute_reply":"2024-01-11T19:58:32.709246Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We will discuss this in more detail in a near future...","metadata":{}},{"cell_type":"code","source":"# TODO: define traininig augmentations \ntrain_transforms = transforms.Compose([\n    transforms.RandomResizedCrop(224),\n    transforms.RandomHorizontalFlip(),\n    transforms.ToTensor(),\n    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])\n])\n\ntest_transforms = transforms.Compose([\n    # TODO: define test augmentations \n    transforms.Resize(256),\n    transforms.CenterCrop(224),\n    transforms.ToTensor(),\n    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])\n])","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:32.711198Z","iopub.execute_input":"2024-01-11T19:58:32.711482Z","iopub.status.idle":"2024-01-11T19:58:32.720503Z","shell.execute_reply.started":"2024-01-11T19:58:32.711458Z","shell.execute_reply":"2024-01-11T19:58:32.719707Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Define the dataset using PIL to read image","metadata":{}},{"cell_type":"code","source":"class CatsDogsDataset(Dataset):\n    def __init__(self, file_list, transform=None):\n        self.file_list = file_list\n        self.transform = transform\n        self.filelength = len(file_list)\n\n    def __len__(self):\n        return self.filelength\n\n    def __getitem__(self, idx):\n        img_path = self.file_list[idx]\n        img = Image.open(img_path)\n        img_transformed = self.transform(img)\n        label = img_path.split(\"/\")[-1].split(\".\")[0]\n        label = 1 if label == \"dog\" else 0\n        return img_transformed, label","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:32.721603Z","iopub.execute_input":"2024-01-11T19:58:32.721884Z","iopub.status.idle":"2024-01-11T19:58:32.731105Z","shell.execute_reply.started":"2024-01-11T19:58:32.721861Z","shell.execute_reply":"2024-01-11T19:58:32.730434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = CatsDogsDataset(train_list, transform=train_transforms)\nvalid_data = CatsDogsDataset(valid_list, transform=test_transforms)\ntest_data = CatsDogsDataset(test_list, transform=test_transforms)","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:32.732247Z","iopub.execute_input":"2024-01-11T19:58:32.732597Z","iopub.status.idle":"2024-01-11T19:58:32.745228Z","shell.execute_reply.started":"2024-01-11T19:58:32.732565Z","shell.execute_reply":"2024-01-11T19:58:32.744515Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Create dataloader, you can modify the batch size if needed","metadata":{}},{"cell_type":"code","source":"batch_size = 32\ntrain_loader = DataLoader(dataset=train_data, batch_size=batch_size, shuffle=True)\nvalid_loader = DataLoader(dataset=valid_data, batch_size=batch_size, shuffle=False)\ntest_loader = DataLoader(dataset=test_data, batch_size=batch_size, shuffle=False)","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:32.748101Z","iopub.execute_input":"2024-01-11T19:58:32.748488Z","iopub.status.idle":"2024-01-11T19:58:32.758056Z","shell.execute_reply.started":"2024-01-11T19:58:32.748463Z","shell.execute_reply":"2024-01-11T19:58:32.757206Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# TODO: define a convolutional neural network, train it and output the log \n# Define a simple CNN model\nclass SimpleCNN(nn.Module):\n    def __init__(self):\n        super(SimpleCNN, self).__init__()\n        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1)\n        self.conv2 = nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1)\n        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)\n        self.fc1 = nn.Linear(32 * 56 * 56, 128)\n        self.fc2 = nn.Linear(128, 2)  # Output has 2 classes: cat and dog\n\n    def forward(self, x):\n        x = F.relu(self.conv1(x))\n        x = self.pool(x)\n        x = F.relu(self.conv2(x))\n        x = self.pool(x)\n        x = x.view(-1, 32 * 56 * 56)  # Reshape before fully connected layer\n        x = F.relu(self.fc1(x))\n        x = self.fc2(x)\n        return x\n\n# Instantiate the model\nmodel = SimpleCNN()\n\n# Define loss function and optimizer\ncriterion = nn.CrossEntropyLoss()\noptimizer = optim.Adam(model.parameters(), lr=0.001)\n\n# Move the model to GPU if available\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\nmodel.to(device)\n\n# Training loop\nnum_epochs = 100\n\nfor epoch in range(num_epochs):\n    model.train()\n    running_loss = 0.0\n    for inputs, labels in train_loader:\n        inputs, labels = inputs.to(device), labels.to(device)\n\n        optimizer.zero_grad()\n\n        outputs = model(inputs)\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)}\")\n\n# Validation loop\nmodel.eval()\npredictions = []\n\nwith torch.no_grad():\n    for inputs, _ in test_loader:\n        inputs = inputs.to(device)\n        outputs = model(inputs)\n        _, predicted = torch.max(outputs.data, 1)\n        predictions.extend(predicted.cpu().numpy())\n\n# Create a DataFrame for submission\nsubmission_df = pd.DataFrame({\n    'id': [os.path.splitext(os.path.basename(file))[0] for file in test_list],\n    'label': predictions\n})\n\n# Save the DataFrame to a CSV file\nsubmission_df.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2024-01-11T19:58:32.759809Z","iopub.execute_input":"2024-01-11T19:58:32.760580Z","iopub.status.idle":"2024-01-11T20:40:26.607232Z","shell.execute_reply.started":"2024-01-11T19:58:32.760554Z","shell.execute_reply":"2024-01-11T20:40:26.606197Z"},"trusted":true},"execution_count":null,"outputs":[]}]}