{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport torch\nfrom torch import nn, optim\nfrom torchvision import datasets, models, transforms\nfrom torch import functional as F\n\nfrom torch.utils.data import Dataset, DataLoader\n\nfrom glob import glob\nfrom PIL import Image\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip -q /kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip\n!unzip -q /kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class CatDataSet(Dataset):\n    def __init__(self, data_dir, transforms):\n        self.image_pathlist = glob(os.path.join(data_dir, '*.jpg'))\n        self.num_images = len(self.image_pathlist)\n        \n        self.transforms = transforms\n        \n    def __len__(self):\n        return self.num_images\n    \n    def get_class(self, path):\n        path = path.split('/')[-1]\n        class_ = path.split('.')[0]\n        if class_== 'cat':\n            return 0.0\n        return 1.0\n\n    \n    def __getitem__(self,idx):\n        path= self.image_pathlist[idx]\n        image=Image.open(path)\n        if self.transforms:\n            image = self.transforms(image)\n        \n        return image, self.get_class(path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_transform = transforms.Compose([\n        transforms.RandomSizedCrop(224),\n        transforms.RandomHorizontalFlip(),\n        transforms.ToTensor(),\n        transforms.Normalize(mean=[0.485, 0.456, 0.406],\n                             std=[0.229, 0.224, 0.225])\n    ])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_ds = CatDataSet('train', data_transform)\nval_ds = CatDataSet('val', data_transform)\n\ndataset_size = {'train': len(train_ds), 'val': len(val_ds)}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dl = DataLoader(train_ds, 8)\nval_dl = DataLoader(val_ds, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = models.resnet18(pretrained=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"in_feats = model.fc.in_features\n\nmodel.fc = nn.Linear(in_feats, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = 5\nlr = 1e-4","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"criterion = nn.BCEWithLogitsLoss()\noptimizer = optim.Adam(model.parameters(), lr)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n\nmodel = model.to(device)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for epoch in range(epochs):\n    print(f\"{epoch}/{epochs-1}\")\n    print(\"-\"*10)\n    \n    running_loss = 0.0\n    for i, (images, labels) in enumerate(train_dl):\n        images = images.to(device)\n        labels = labels.to(device)\n        labels = labels.view(len(labels), 1)\n        \n        optimizer.zero_grad()\n        \n        logits = model(images)\n        loss = criterion(logits, labels)\n        running_loss += loss.item() * images.size(0)\n        \n        loss.backward()\n        optimizer.step()\n        \n        if i%200==0:\n            print(f'Loss at step {i} - {loss.item()}')\n\n    epoch_loss = running_loss / dataset_size['train']\n    print(f\"Train loss: {epoch_loss}\")\n    \n    \n    running_loss = 0.0\n    for images, labels in val_dl:\n        images = images.to(device)\n        labels = labels.to(device)\n        labels = labels.view(len(labels), 1)\n                \n        logits = model(images)\n        loss = criterion(logits, labels)\n        running_loss += loss.item() * images.size(0)\n\n    epoch_loss = running_loss / dataset_size['val']\n    print(f\"Val loss: {epoch_loss}\")\n    \n    print()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}