{"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":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/xxxxxxxyyyyyyyyy/dogvscat-morsonsebastiano\n\nWandb link: https://wandb.ai/monkeys777/DOGS_VS_CAT?workspace=user-sebastiano-mors","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":"2024-01-13T14:01:51.464881Z","iopub.execute_input":"2024-01-13T14:01:51.465320Z","iopub.status.idle":"2024-01-13T14:01:51.472740Z","shell.execute_reply.started":"2024-01-13T14:01:51.465286Z","shell.execute_reply":"2024-01-13T14:01:51.471821Z"},"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\nfrom torchvision.transforms import v2\n\nimport wandb\nfrom kaggle_secrets import UserSecretsClient\n\nuser_secrets = UserSecretsClient()\nsecret_value_0 = user_secrets.get_secret(\"wandb.api.key\")\nwandb.login(key=secret_value_0)\nwandb.init(project='DOGS_VS_CAT', save_code=True)\n\nnp.random.seed(0)\ntorch.manual_seed(0)\ntorch.cuda.manual_seed(0)","metadata":{"execution":{"iopub.status.busy":"2024-01-13T14:01:51.476298Z","iopub.execute_input":"2024-01-13T14:01:51.476578Z","iopub.status.idle":"2024-01-13T14:02:08.576741Z","shell.execute_reply.started":"2024-01-13T14:01:51.476553Z","shell.execute_reply":"2024-01-13T14:02:08.574193Z"},"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":"2024-01-13T14:02:08.577647Z","iopub.status.idle":"2024-01-13T14:02:08.578011Z","shell.execute_reply.started":"2024-01-13T14:02:08.577840Z","shell.execute_reply":"2024-01-13T14:02:08.577857Z"},"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":"2024-01-13T14:02:08.579949Z","iopub.status.idle":"2024-01-13T14:02:08.580845Z","shell.execute_reply.started":"2024-01-13T14:02:08.580584Z","shell.execute_reply":"2024-01-13T14:02:08.580608Z"},"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":"2024-01-13T14:02:08.582261Z","iopub.status.idle":"2024-01-13T14:02:08.582732Z","shell.execute_reply.started":"2024-01-13T14:02:08.582470Z","shell.execute_reply":"2024-01-13T14:02:08.582491Z"},"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":"2024-01-13T14:02:08.584142Z","iopub.status.idle":"2024-01-13T14:02:08.584671Z","shell.execute_reply.started":"2024-01-13T14:02:08.584390Z","shell.execute_reply":"2024-01-13T14:02:08.584413Z"},"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":"2024-01-13T14:02:08.585832Z","iopub.status.idle":"2024-01-13T14:02:08.586297Z","shell.execute_reply.started":"2024-01-13T14:02:08.586046Z","shell.execute_reply":"2024-01-13T14:02:08.586068Z"},"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 = v2.Compose([v2.ToPILImage(),\n                               v2.RandomResizedCrop(size=((128, 128)), antialias=True),\n                               v2.ToTensor(), \n                               v2.Normalize(mean=(0.5,), std=(0.5,))\n])\n\ntest_transforms = v2.Compose([ v2.ToPILImage(),\n                               v2.RandomResizedCrop(size=((128, 128)), antialias=True),\n                               v2.ToTensor(), \n                               v2.Normalize(mean=(0.5,), std=(0.5,))\n])","metadata":{"execution":{"iopub.status.busy":"2024-01-13T14:02:08.587314Z","iopub.status.idle":"2024-01-13T14:02:08.587755Z","shell.execute_reply.started":"2024-01-13T14:02:08.587520Z","shell.execute_reply":"2024-01-13T14:02:08.587541Z"},"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":"2024-01-13T14:02:08.588906Z","iopub.status.idle":"2024-01-13T14:02:08.589365Z","shell.execute_reply.started":"2024-01-13T14:02:08.589115Z","shell.execute_reply":"2024-01-13T14:02:08.589154Z"},"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)\n","metadata":{"execution":{"iopub.status.busy":"2024-01-13T14:02:08.590522Z","iopub.status.idle":"2024-01-13T14:02:08.590972Z","shell.execute_reply.started":"2024-01-13T14:02:08.590734Z","shell.execute_reply":"2024-01-13T14:02:08.590755Z"},"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":"2024-01-13T14:02:08.591879Z","iopub.status.idle":"2024-01-13T14:02:08.592327Z","shell.execute_reply.started":"2024-01-13T14:02:08.592083Z","shell.execute_reply":"2024-01-13T14:02:08.592104Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# CNN \n#TODO: define a convolutional neural network, train it and output the log ","metadata":{}},{"cell_type":"code","source":"from torch.nn import *\nnumChannels = 3\nclasses=2\n\nclass Net(torch.nn.Module):\n    def __init__(self):\n        super(Net, self).__init__()\n        # initialize first set of CONV => RELU => POOL layers\n        self.conv1 = Conv2d(in_channels=numChannels, out_channels=20,\n            kernel_size=(5, 5), padding=1)\n        self.relu1 = ReLU()\n        self.maxpool1 = MaxPool2d(kernel_size=(2, 2), stride=(2, 2))\n        # initialize second set of CONV => RELU => POOL layers\n        self.conv2 = Conv2d(in_channels=20, out_channels=50,\n            kernel_size=(5, 5))\n        self.relu2 = ReLU()\n        self.maxpool2 = MaxPool2d(kernel_size=(2, 2), stride=(2, 2))\n        # initialize first (and only) set of FC => RELU layers\n        self.fc1 = Linear(in_features=42050, out_features=500)\n        self.relu3 = ReLU()\n        # initialize our softmax classifier\n        self.fc2 = Linear(in_features=500, out_features=classes)\n        self.logSoftmax = LogSoftmax(dim=1)\n\n    def forward(self, x):\n        x = x.to(device='cuda')\n        # pass the input through our first set of CONV => RELU =>\n        # POOL layers\n        x = self.conv1(x)\n        x = self.relu1(x)\n        x = self.maxpool1(x)\n        # pass the output from the previous layer through the second\n        # set of CONV => RELU => POOL layers\n        x = self.conv2(x)\n        x = self.relu2(x)\n        x = self.maxpool2(x)\n        # flatten the output from the previous layer and pass it\n        # through our only set of FC => RELU layers\n        x = torch.flatten(x, 1)\n        x = self.fc1(x)\n        x = self.relu3(x)\n        # pass the output to our softmax classifier to get our output\n        # predictions\n        x = self.fc2(x)\n        output = self.logSoftmax(x)\n        # return the output predictions\n        return output\n        ","metadata":{"execution":{"iopub.status.busy":"2024-01-13T14:02:08.593744Z","iopub.status.idle":"2024-01-13T14:02:08.594199Z","shell.execute_reply.started":"2024-01-13T14:02:08.593954Z","shell.execute_reply":"2024-01-13T14:02:08.593975Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"criterion = nn.CrossEntropyLoss()\n#criterion = nn.NLLLoss()\ndef train(model, device, train_loader, opt, epoch):\n    mean_train_losses = []\n    mean_valid_losses = []\n    valid_acc_list = []\n    train_losses = []\n    valid_losses = []\n    model.train()\n    for batch_id, (images, target) in enumerate(train_loader):\n        images, target = images.to(device), target.to(device)\n\n        opt.zero_grad()\n        output = model(images)\n        loss = criterion(output,target)\n        loss.backward()\n        opt.step()\n        train_losses.append(loss.item())\n        \n    model.eval()\n    val_losses = 0\n    val_correct = 0\n    correct = 0\n    total = 0\n    with torch.no_grad():\n        \n        for batch_id, data in enumerate (valid_loader):\n            \n            images, target = images.to(device), target.to(device)\n            output = model(images)\n            # calculate the loss\n            loss = criterion(output, target)\n            # update running validation loss \n            valid_losses.append(loss.item())\n            \n            _, predicted = torch.max(output.data, 1)\n            correct += (predicted == target).sum().item()\n            total += target.size(0)\n\n    mean_train_losses.append(np.mean(train_losses))\n    mean_valid_losses.append(np.mean(valid_losses))\n    \n    accuracy = 100*correct/total\n    valid_acc_list.append(accuracy)\n    print('epoch : {}, train loss : {:.4f}, valid loss : {:.4f}, valid acc : {:.2f}%'\\\n         .format(epoch+1, np.mean(train_losses), np.mean(valid_losses), accuracy))\n    \n    wandb.log({'train_loss':mean_train_losses[-1]})\n    wandb.log({'val_loss':mean_valid_losses[-1]})\n    wandb.log({'val_accuracy':valid_acc_list[-1]})\n        \ndef test(model, device, test_loader):\n    model.eval()\n    test_loss = 0\n    correct = 0\n    with torch.no_grad():\n        for batch_id, (images, target) in test_loader:\n            images, target = images.to(device), target.to(device)\n            output = model(images)\n            test_loss += F.nll_loss(output, target, reduction='sum').item()\n            pred = output.argmax(dim=1, keepdim=True)\n            correct += pred.eq(target.view_as(pred)).sum().item()\n\n    test_loss /= len(test_loader.dataset)\n\n    print('\\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\\n'.format(\n        test_loss, correct, len(test_loader.dataset),\n        100. * correct / len(test_loader.dataset)))\n    return test_loss","metadata":{"execution":{"iopub.status.busy":"2024-01-13T14:02:08.595358Z","iopub.status.idle":"2024-01-13T14:02:08.595812Z","shell.execute_reply.started":"2024-01-13T14:02:08.595571Z","shell.execute_reply":"2024-01-13T14:02:08.595591Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from torch.optim.lr_scheduler import StepLR\n\nlr = 0.1\nstep_size = 1\ngamma=0.7\nepoch = 10\nopt = \"SGD\" # \"Adam\"\n\nsaved = False #True if I want to use a saved model\n\ndev_name = \"cuda\" if torch.cuda.is_available() else \"mps\" if torch.backends.mps.is_available() else \"cpu\"\nprint(\"Using {} to traing the model\".format(dev_name))\ndevice = torch.device(dev_name)\n\nmodel = Net().to(device)\n\n\nif not saved:\n    \n    wandb.log({'lr': lr})\n    wandb.log({'step_size': step_size})\n    wandb.log({'gamma': gamma})\n    wandb.log({'epoch': epoch})\n    wandb.log({'optimizer': opt})\n\n\n    if opt == \"Adam\":\n        opt = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=0.5)\n    elif opt == \"SGD\":\n        opt = torch.optim.SGD(model.parameters(), lr=lr,momentum=0.1)\n\n\n    # Decreases the learning rate of each parameter group by gamma every 1 epoch\n    #scheduler = StepLR(opt, step_size=step_size, gamma=gamma)\n    for epoch in range(0, epoch):\n        train(model, device, train_loader, opt, epoch)\n        #scheduler.step()\n    \n    #torch.save(model.state_dict(), \"/kaggle/input/digit-recognizer/model\")\n\n    \nelse:\n    print(\"Miaoooo\")\n    #model.load_state_dict(torch.load(\"/kaggle/input/digit-recognizer/model\"))","metadata":{"execution":{"iopub.status.busy":"2024-01-13T14:02:08.597385Z","iopub.status.idle":"2024-01-13T14:02:08.597852Z","shell.execute_reply.started":"2024-01-13T14:02:08.597597Z","shell.execute_reply":"2024-01-13T14:02:08.597620Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import math\nwith torch.no_grad():\n    model.eval()\n    test_pred = torch.LongTensor()\n    for i,(images, target) in enumerate(test_loader):\n        output = torch.exp(model(images))\n        #print(\"OUTPUT: \", torch.exp(output))\n        \n        predicted =  torch.Tensor([x[0] for x in output])\n        #print(\"PREDICTED: \", predicted)\n        predicted = predicted.cpu()\n        \n        test_pred = torch.cat((test_pred, predicted), dim=0)\n    ","metadata":{"execution":{"iopub.status.busy":"2024-01-13T14:02:08.598931Z","iopub.status.idle":"2024-01-13T14:02:08.599387Z","shell.execute_reply.started":"2024-01-13T14:02:08.599153Z","shell.execute_reply":"2024-01-13T14:02:08.599174Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"out_df = pd.DataFrame(np.c_[np.arange(1, len(test_data)+1)[:,None], test_pred.numpy()], columns=['id', 'Label'])\nout_df['id'] = out_df['id'].astype(int)\nout_df.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2024-01-13T14:02:08.600794Z","iopub.status.idle":"2024-01-13T14:02:08.601254Z","shell.execute_reply.started":"2024-01-13T14:02:08.601004Z","shell.execute_reply":"2024-01-13T14:02:08.601024Z"},"trusted":true},"execution_count":null,"outputs":[]}]}