{"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":30627,"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":"2024-01-15T16:19:29.010349Z","iopub.execute_input":"2024-01-15T16:19:29.010736Z","iopub.status.idle":"2024-01-15T16:19:29.031618Z","shell.execute_reply.started":"2024-01-15T16:19:29.01071Z","shell.execute_reply":"2024-01-15T16:19:29.030588Z"},"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":"2024-01-15T16:19:29.036458Z","iopub.execute_input":"2024-01-15T16:19:29.036829Z","iopub.status.idle":"2024-01-15T16:19:31.800833Z","shell.execute_reply.started":"2024-01-15T16:19:29.036793Z","shell.execute_reply":"2024-01-15T16:19:31.799755Z"},"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":"2024-01-15T16:19:31.802473Z","iopub.execute_input":"2024-01-15T16:19:31.80315Z","iopub.status.idle":"2024-01-15T16:19:47.584416Z","shell.execute_reply.started":"2024-01-15T16:19:31.803107Z","shell.execute_reply":"2024-01-15T16:19:47.583347Z"},"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":"2024-01-15T16:19:47.586935Z","iopub.execute_input":"2024-01-15T16:19:47.587333Z","iopub.status.idle":"2024-01-15T16:19:47.616843Z","shell.execute_reply.started":"2024-01-15T16:19:47.587281Z","shell.execute_reply":"2024-01-15T16:19:47.615772Z"},"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":"2024-01-15T16:19:47.618189Z","iopub.execute_input":"2024-01-15T16:19:47.618584Z","iopub.status.idle":"2024-01-15T16:19:50.182472Z","shell.execute_reply.started":"2024-01-15T16:19:47.618545Z","shell.execute_reply":"2024-01-15T16:19:50.181072Z"},"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":"2024-01-15T16:19:50.183925Z","iopub.execute_input":"2024-01-15T16:19:50.184265Z","iopub.status.idle":"2024-01-15T16:19:50.227452Z","shell.execute_reply.started":"2024-01-15T16:19:50.184237Z","shell.execute_reply":"2024-01-15T16:19:50.226492Z"},"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":"2024-01-15T16:19:50.228799Z","iopub.execute_input":"2024-01-15T16:19:50.229547Z","iopub.status.idle":"2024-01-15T16:19:50.236491Z","shell.execute_reply.started":"2024-01-15T16:19:50.229514Z","shell.execute_reply":"2024-01-15T16:19:50.235423Z"},"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":"train_transforms = transforms.Compose([\n    # TODO: define traininig augmentations \n    \n    transforms.RandomResizedCrop(224),\n    transforms.RandomHorizontalFlip(),\n    transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2, hue=0.2),\n    transforms.RandomRotation(degrees=15),\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    \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])\n","metadata":{"execution":{"iopub.status.busy":"2024-01-15T16:19:50.239194Z","iopub.execute_input":"2024-01-15T16:19:50.240113Z","iopub.status.idle":"2024-01-15T16:19:50.24952Z","shell.execute_reply.started":"2024-01-15T16:19:50.240081Z","shell.execute_reply":"2024-01-15T16:19:50.247704Z"},"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":"2024-01-15T16:19:50.25105Z","iopub.execute_input":"2024-01-15T16:19:50.251874Z","iopub.status.idle":"2024-01-15T16:19:50.261748Z","shell.execute_reply.started":"2024-01-15T16:19:50.25184Z","shell.execute_reply":"2024-01-15T16:19:50.260906Z"},"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":"2024-01-15T16:19:50.264327Z","iopub.execute_input":"2024-01-15T16:19:50.264991Z","iopub.status.idle":"2024-01-15T16:19:50.279142Z","shell.execute_reply.started":"2024-01-15T16:19:50.26496Z","shell.execute_reply":"2024-01-15T16:19:50.278027Z"},"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":"2024-01-15T16:19:50.28184Z","iopub.execute_input":"2024-01-15T16:19:50.28215Z","iopub.status.idle":"2024-01-15T16:19:50.291912Z","shell.execute_reply.started":"2024-01-15T16:19:50.282118Z","shell.execute_reply":"2024-01-15T16:19:50.290933Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import wandb\nimport pandas as pd\n\n# Initialize WandB\nwandb.init(project='dogs-vs-cats')\n\n","metadata":{"execution":{"iopub.status.busy":"2024-01-15T18:36:51.811055Z","iopub.execute_input":"2024-01-15T18:36:51.811886Z","iopub.status.idle":"2024-01-15T18:37:26.882824Z","shell.execute_reply.started":"2024-01-15T18:36:51.811854Z","shell.execute_reply":"2024-01-15T18:37:26.881764Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# TODO: define a convolutional neural network, train it and output the log\n\n# Define neural network model\nclass SimpleCNN(nn.Module):\n    def __init__(self):\n        super(SimpleCNN, self).__init__()\n        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1)\n        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)\n        self.fc1 = nn.Linear(64 * 112 * 112, 2)  \n\n    def forward(self, x):\n        x = F.relu(self.conv1(x))\n        x = self.pool(x)\n        x = x.view(-1, 64 * 112 * 112)  \n        x = self.fc1(x)\n        return x\n    \n# Initialize the model, loss function, and optimizer\nmodel = SimpleCNN()\ncriterion = nn.CrossEntropyLoss()\noptimizer = optim.Adam(model.parameters(), lr=0.001)\n\n# Move model to GPU if available\ndevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\nmodel.to(device)\n\n# Training loop and validation loop\nepochs = 10\n\nfor epoch in range(epochs):\n    # Training\n    model.train()\n    for i, (inputs, labels) in enumerate(train_loader):\n        inputs, labels = inputs.to(device), labels.to(device)\n\n        optimizer.zero_grad()\n        outputs = model(inputs)\n        loss = criterion(outputs, labels)\n        loss.backward()\n        optimizer.step()\n\n    # Validation\n    model.eval()\n    with torch.no_grad():\n        for inputs, labels in valid_loader:\n            inputs, labels = inputs.to(device), labels.to(device)\n\n            outputs = model(inputs)\n            val_loss = criterion(outputs, labels)\n\n    # Log metrics to WandB\n    wandb.log({\"epoch\": epoch+1, \"train_loss\": loss.item(), \"val_loss\": val_loss.item()})\n\n","metadata":{"execution":{"iopub.status.busy":"2024-01-15T18:37:35.554804Z","iopub.execute_input":"2024-01-15T18:37:35.555627Z","iopub.status.idle":"2024-01-15T19:11:23.069705Z","shell.execute_reply.started":"2024-01-15T18:37:35.555589Z","shell.execute_reply":"2024-01-15T19:11:23.06858Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Test the model on the test set\nmodel.eval()\nprobabilities = []\n\nwith torch.no_grad():\n    for inputs, _ in test_loader:\n        inputs = inputs.to(device)\n        outputs = model(inputs)\n        probs = F.softmax(outputs, dim=1)\n        probabilities.extend(probs[:, 1].cpu().numpy())\n\n# Save probabilities to a CSV file\nprobabilities_df = pd.DataFrame({\"id\": range(1, len(probabilities)+1), \"label\": probabilities})\nprobabilities_df.to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2024-01-15T19:22:08.262916Z","iopub.execute_input":"2024-01-15T19:22:08.263296Z","iopub.status.idle":"2024-01-15T19:23:01.544216Z","shell.execute_reply.started":"2024-01-15T19:22:08.263269Z","shell.execute_reply":"2024-01-15T19:23:01.543342Z"},"trusted":true},"execution_count":null,"outputs":[]}]}