{"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":"gpu","dataSources":[{"sourceId":5441,"databundleVersionId":38425,"sourceType":"competition"}],"dockerImageVersionId":30635,"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":"2024-01-15T21:30:46.688661Z","iopub.execute_input":"2024-01-15T21:30:46.689157Z","iopub.status.idle":"2024-01-15T21:30:46.699402Z","shell.execute_reply.started":"2024-01-15T21:30:46.689099Z","shell.execute_reply":"2024-01-15T21:30:46.698511Z"},"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":"2024-01-15T21:30:46.701079Z","iopub.execute_input":"2024-01-15T21:30:46.701465Z","iopub.status.idle":"2024-01-15T21:30:46.712161Z","shell.execute_reply.started":"2024-01-15T21:30:46.701436Z","shell.execute_reply":"2024-01-15T21:30:46.711173Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import wandb\n\nconfig = {\n    \"learning_rate\": 0.001,\n    \"epochs\": 11,\n    \"optimizer\": \"Adam\",\n    \"kernel_sizes\": [3,3,3],\n    \"activation\": \"ReLU\",\n    \"dropout\": 0.5,\n    \"batch_size\": 32,\n}\n#mode=\"disabled\" to enable for version saving etc.\nwandb.init(project='CATSnDOGS_v1', save_code=True, config=config, mode=\"disabled\")","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:30:46.713824Z","iopub.execute_input":"2024-01-15T21:30:46.714186Z","iopub.status.idle":"2024-01-15T21:31:22.415933Z","shell.execute_reply.started":"2024-01-15T21:30:46.714158Z","shell.execute_reply":"2024-01-15T21:31:22.414816Z"},"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":"2024-01-15T21:31:22.418234Z","iopub.execute_input":"2024-01-15T21:31:22.419211Z","iopub.status.idle":"2024-01-15T21:31:34.548240Z","shell.execute_reply.started":"2024-01-15T21:31:22.419171Z","shell.execute_reply":"2024-01-15T21:31:34.547121Z"},"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":"2024-01-15T21:31:34.549516Z","iopub.execute_input":"2024-01-15T21:31:34.549830Z","iopub.status.idle":"2024-01-15T21:31:34.577605Z","shell.execute_reply.started":"2024-01-15T21:31:34.549803Z","shell.execute_reply":"2024-01-15T21:31:34.576586Z"},"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":"2024-01-15T21:31:34.580637Z","iopub.execute_input":"2024-01-15T21:31:34.581299Z","iopub.status.idle":"2024-01-15T21:31:37.709353Z","shell.execute_reply.started":"2024-01-15T21:31:34.581247Z","shell.execute_reply":"2024-01-15T21:31:37.708066Z"},"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":"2024-01-15T21:31:37.710643Z","iopub.execute_input":"2024-01-15T21:31:37.711432Z","iopub.status.idle":"2024-01-15T21:31:37.752668Z","shell.execute_reply.started":"2024-01-15T21:31:37.711394Z","shell.execute_reply":"2024-01-15T21:31:37.751834Z"},"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":"2024-01-15T21:31:37.754203Z","iopub.execute_input":"2024-01-15T21:31:37.754993Z","iopub.status.idle":"2024-01-15T21:31:37.762071Z","shell.execute_reply.started":"2024-01-15T21:31:37.754933Z","shell.execute_reply":"2024-01-15T21:31:37.761160Z"},"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":"# Define some image properties\nimage_height = 256\nimage_width = 256\nimage_channels = 3 #rgb","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:31:37.763537Z","iopub.execute_input":"2024-01-15T21:31:37.764169Z","iopub.status.idle":"2024-01-15T21:31:37.771220Z","shell.execute_reply.started":"2024-01-15T21:31:37.764129Z","shell.execute_reply":"2024-01-15T21:31:37.770320Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_transforms = transforms.Compose([\n    # TODO: define traininig augmentations\n    transforms.Resize((image_height, image_width)),\n    transforms.RandomHorizontalFlip(),\n    transforms.ToTensor()\n    #Maybe random horizontal flip\n])\n\ntest_transforms = transforms.Compose([\n    # TODO: define test augmentations\n    transforms.Resize((256,256)),\n    transforms.ToTensor()\n])","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:31:37.772670Z","iopub.execute_input":"2024-01-15T21:31:37.773307Z","iopub.status.idle":"2024-01-15T21:31:37.781928Z","shell.execute_reply.started":"2024-01-15T21:31:37.773272Z","shell.execute_reply":"2024-01-15T21:31:37.781027Z"},"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":"2024-01-15T21:31:37.783443Z","iopub.execute_input":"2024-01-15T21:31:37.784083Z","iopub.status.idle":"2024-01-15T21:31:37.793704Z","shell.execute_reply.started":"2024-01-15T21:31:37.784048Z","shell.execute_reply":"2024-01-15T21:31:37.792758Z"},"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":"2024-01-15T21:31:37.798114Z","iopub.execute_input":"2024-01-15T21:31:37.798469Z","iopub.status.idle":"2024-01-15T21:31:37.805893Z","shell.execute_reply.started":"2024-01-15T21:31:37.798442Z","shell.execute_reply":"2024-01-15T21:31:37.805011Z"},"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 = wandb.config[\"batch_size\"]\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":"2024-01-15T21:31:37.807044Z","iopub.execute_input":"2024-01-15T21:31:37.807561Z","iopub.status.idle":"2024-01-15T21:31:37.816665Z","shell.execute_reply.started":"2024-01-15T21:31:37.807526Z","shell.execute_reply":"2024-01-15T21:31:37.815945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data[0][0].shape","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:31:37.817825Z","iopub.execute_input":"2024-01-15T21:31:37.818786Z","iopub.status.idle":"2024-01-15T21:31:37.836899Z","shell.execute_reply.started":"2024-01-15T21:31:37.818751Z","shell.execute_reply":"2024-01-15T21:31:37.836024Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport torchvision.utils as vutils\n\n# Skapa en itererbar\ntrain_iter = iter(train_loader)\n\n# Hämta de första fem batcherna från dataloader\nfor i in range(1):\n    # Hämta ett batch från dataloader\n    images, labels = next(train_iter)\n\n    # Visa bilderna i batchen\n    plt.figure(figsize=(10, 5))\n    plt.title(f\"Batch {i+1}\")\n    plt.axis(\"off\")\n    plt.imshow(vutils.make_grid(images, padding=5, normalize=True).permute(1, 2, 0))\n    plt.show()\n\n    # Visa labels för varje bild i batchen\n    for j in range(len(labels)):\n        print(f\"Label {j+1} in Batch {i+1}: {labels[j].item()}\")\n","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:31:37.838422Z","iopub.execute_input":"2024-01-15T21:31:37.839064Z","iopub.status.idle":"2024-01-15T21:31:38.869194Z","shell.execute_reply.started":"2024-01-15T21:31:37.839029Z","shell.execute_reply":"2024-01-15T21:31:38.868155Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# TODO: define a convolutional neural network, train it and output the log ","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:31:38.870436Z","iopub.execute_input":"2024-01-15T21:31:38.870784Z","iopub.status.idle":"2024-01-15T21:31:38.875015Z","shell.execute_reply.started":"2024-01-15T21:31:38.870750Z","shell.execute_reply":"2024-01-15T21:31:38.874168Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"m = nn.Dropout(p=0.2)\ninput = torch.randn(20, 16)\noutput = m(input)\n\nzeros_mask = torch.eq(output, 0)\nnum_zeros_output = torch.sum(zeros_mask).item()\n\nzeros_mask = torch.eq(input, 0)\nnum_zeros_input = torch.sum(zeros_mask).item()\nprint(\"Zeros input:\", num_zeros_input, \"Zeros after dropout:\", num_zeros_output)","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:31:38.876261Z","iopub.execute_input":"2024-01-15T21:31:38.876779Z","iopub.status.idle":"2024-01-15T21:31:38.890033Z","shell.execute_reply.started":"2024-01-15T21:31:38.876746Z","shell.execute_reply":"2024-01-15T21:31:38.888922Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def init_layer(m):\n    nn.init.xavier_uniform_(m.weight)\n    m.bias.data.zero_()\n    return m\n\nclass CNNet(nn.Module):\n    def __init__(self):\n        super(CNNet,self).__init__()\n        \n        self.convLayer1 = nn.Sequential(\n            nn.Conv2d(3,16,kernel_size=3, padding=0,stride=2),\n            nn.BatchNorm2d(16),\n            nn.ReLU(),\n            nn.MaxPool2d(2) #The strade is default = kernel_size = 2\n        )\n        \n        self.convLayer2 = nn.Sequential(\n            nn.Conv2d(16,32, kernel_size=3, padding=0, stride=2),\n            nn.BatchNorm2d(32),\n            nn.ReLU(),\n            nn.MaxPool2d(2)\n            )\n        \n        self.convLayer3 = nn.Sequential(\n            nn.Conv2d(32,32, kernel_size=3, padding=0, stride=2),\n            nn.BatchNorm2d(32),\n            nn.ReLU(),\n            #nn.MaxPool2d(2)\n            )\n        \n        self.convLayer4 = nn.Sequential(\n            nn.Conv2d(32,64, kernel_size=3, padding=0, stride=1),\n            nn.BatchNorm2d(64),\n            nn.ReLU(),\n            nn.MaxPool2d(2, stride=1)\n        )\n        \n        \n        self.linLayer1 = init_layer(nn.Linear(4*4*64,10))\n        self.dropout = nn.Dropout(0.5)\n        self.linLayer2 = init_layer(nn.Linear(10,2))\n        self.relu = nn.ReLU()\n        \n        \n    def forward(self,x):\n        out = self.convLayer1(x)\n        out = self.dropout(self.convLayer2(out))\n        out = self.convLayer3(out)\n        out = self.convLayer4(out)\n        out = out.view(out.size(0),-1)\n        out = self.dropout(self.relu(self.linLayer1(out)))\n        out = self.linLayer2(out)\n        return out","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:31:38.891695Z","iopub.execute_input":"2024-01-15T21:31:38.892083Z","iopub.status.idle":"2024-01-15T21:31:38.908922Z","shell.execute_reply.started":"2024-01-15T21:31:38.892048Z","shell.execute_reply":"2024-01-15T21:31:38.907851Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device = 'cuda' if torch.cuda.is_available() else 'cpu'\nprint(device)","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:31:38.910513Z","iopub.execute_input":"2024-01-15T21:31:38.910903Z","iopub.status.idle":"2024-01-15T21:31:38.919199Z","shell.execute_reply.started":"2024-01-15T21:31:38.910857Z","shell.execute_reply":"2024-01-15T21:31:38.918235Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Training\nnet = CNNet().to(device)\nlr = wandb.config[\"learning_rate\"]\nepochs = wandb.config[\"epochs\"]\n\ncriterion = nn.CrossEntropyLoss()\noptimizer = torch.optim.Adam(net.parameters(), lr=lr)\n\nfor epoch in range(epochs):\n    epoch_loss = 0\n    epoch_accuracy = 0\n    net.train()\n    for x_train, y_train in train_loader:\n        x_train = x_train.to(device)\n        y_train = y_train.to(device)\n        \n        y_pred = net(x_train)\n        loss = criterion(y_pred, y_train)\n        \n        optimizer.zero_grad()\n        loss.backward()\n        optimizer.step()\n        \n        acc = ((y_pred.argmax(dim=1) == y_train).float().mean())\n        epoch_accuracy += acc/len(train_loader)\n        epoch_loss += loss/len(train_loader)\n        \n    print('Epoch : {}, train accuracy : {}, train loss : {}'.format(epoch+1, epoch_accuracy,epoch_loss))\n    wandb.log({\"train_accuracy\": epoch_accuracy, \"train_loss\": epoch_loss})\n    \n    net.eval()\n    with torch.no_grad():\n        epoch_val_accuracy=0\n        epoch_val_loss =0\n        for x_train, y_train in valid_loader:\n            x_train = x_train.to(device)\n            y_train = y_train.to(device)\n            \n            val_preds = net(x_train)\n            val_loss = criterion(val_preds,y_train)\n            \n            \n            acc = ((val_preds.argmax(dim=1) == y_train).float().mean())\n            epoch_val_accuracy += acc/ len(valid_loader)\n            epoch_val_loss += val_loss/ len(valid_loader)\n            \n        print('Epoch : {}, val_accuracy : {}, val_loss : {}'.format(epoch+1, epoch_val_accuracy,epoch_val_loss))\n        wandb.log({\"val_accuracy\": epoch_val_accuracy, \"val_loss\": epoch_val_loss})","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:31:38.920459Z","iopub.execute_input":"2024-01-15T21:31:38.920839Z","iopub.status.idle":"2024-01-15T21:48:11.497340Z","shell.execute_reply.started":"2024-01-15T21:31:38.920806Z","shell.execute_reply":"2024-01-15T21:48:11.495424Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with torch.no_grad():\n    net.eval()\n    test_pred = torch.LongTensor()\n    for i, data in enumerate(test_loader):\n        output = F.softmax(net(data[0].to(device)), dim=1)[..., 1]\n        predicted = output.cpu()\n        test_pred = torch.cat((test_pred, predicted), dim=0)\n    out_df = pd.DataFrame(np.c_[np.arange(1, len(test_data)+1)[:,None], test_pred.numpy()], columns=['id', 'label']).astype({'id':'int'})\n    out_df.to_csv('submission.csv', index=False)\nprint(\"SUBMISSION FILE READY\")\nwandb.finish()","metadata":{"execution":{"iopub.status.busy":"2024-01-15T21:48:11.499083Z","iopub.execute_input":"2024-01-15T21:48:11.499666Z","iopub.status.idle":"2024-01-15T21:49:01.228988Z","shell.execute_reply.started":"2024-01-15T21:48:11.499631Z","shell.execute_reply":"2024-01-15T21:49:01.228218Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}