{"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_minor":4,"nbformat":4,"cells":[{"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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport zipfile\nimport random\nimport matplotlib.pyplot as plt\nimport torch\nfrom torch.utils.data import Dataset\nfrom skimage import io\nimport torch.nn as nn\nimport torch.optim as optim\nfrom torch.utils.data import DataLoader\nimport torchvision.transforms as transforms\nimport torchvision.models as models\nimport torchvision\nimport torch.nn.functional as F","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# extract all contents of zip file\ntrain_path = \"../input/dogs-vs-cats/train.zip\"\nzip_train = zipfile.ZipFile(train_path, 'r')\nzip_train.extractall(\"./\")\nzip_train.close()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# now we have a folder called train in our root dir\n#let's find the contents of the folder\ntrain_img_names = os.listdir(\"./train\")\ntrain_img_names[0:10]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(train_img_names)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img = random.choice(train_img_names)\nplt.imshow(plt.imread(\"./train/\"+img))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(plt.imread(\"./train/\"+img).shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# preparing training data\ncategories = []\nfor img in train_img_names:\n    if img.split(\".\")[0] == \"dog\":\n        categories.append(1)\n    else:\n        categories.append(0)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.DataFrame({\n    'filename': train_img_names,\n    'category': categories\n})","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df['category'].value_counts().plot.bar()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class CatsAndDogsDataset(Dataset):\n    def __init__(self, df, root_dir, transform=None):\n        self.annotations = df\n        self.root_dir = root_dir\n        self.transform = transform\n\n    def __len__(self):\n        return len(self.annotations)\n\n    def __getitem__(self, index):\n        img_path = os.path.join(self.root_dir, self.annotations.iloc[index,0])\n        image = io.imread(img_path)\n        y_label = torch.tensor(int(self.annotations.iloc[index,1]))\n\n        if self.transform:\n            image = self.transform(image)\n\n        return (image, y_label)\n        ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# hyper parameters\nin_channel = 3\nnum_classes = 2\nlearning_rate = 0.001\nbatch_size = 32\nnum_epochs = 10","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_transform = transforms.Compose([\n    transforms.ToPILImage(),\n    transforms.Resize(256),\n    transforms.ColorJitter(),\n    transforms.RandomCrop(224),\n    transforms.RandomHorizontalFlip(),\n    transforms.ToTensor()\n])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load data\ndataset = CatsAndDogsDataset(df = df, root_dir = \"./train\", transform = data_transform)\ntrain_set, val_set = torch.utils.data.random_split(dataset, [20000, 5000])\ntrain_loader = DataLoader(dataset=train_set, batch_size=batch_size, shuffle=True)\nval_loader = DataLoader(dataset=val_set)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"samples, labels = iter(train_loader).next()\nplt.figure(figsize=(16,24))\ngrid_imgs = torchvision.utils.make_grid(samples[:24])\nnp_grid_imgs = grid_imgs.numpy()\n# in tensor, image is (batch, width, height), so you have to transpose it to (width, height, batch) in numpy to show it.\nplt.imshow(np.transpose(np_grid_imgs, (1,2,0)))\nprint(samples[0].shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = models.resnet18(pretrained=True)\nnum_ftrs = model.fc.in_features","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fc = nn.Linear(num_ftrs,2)\nmodel.to(device)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Loss and optimizer\ncriterion = nn.CrossEntropyLoss()\noptimizer = optim.Adam(model.parameters(), lr=learning_rate)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Train the network\nfor epoch in range(num_epochs):\n    print(f\"Epoch {epoch}\")\n    for batch_idx, (data, targets) in enumerate(train_loader):\n        # get data to cuda\n        data = data.to(device)\n        targets = targets.to(device)\n\n        # forward\n        scores = model(data)\n        loss = criterion(scores, targets)\n\n        # backward\n        optimizer.zero_grad() #set all gradients to zero for each batch\n        loss.backward()\n\n        # gradient descend or adam step\n        optimizer.step()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Check accuracy on training to see how good our model is\ndef check_accuracy(loader, model):\n    num_correct = 0\n    num_samples = 0\n    model.eval()\n\n    with torch.no_grad():\n        for x, y in loader:\n            x = x.to(device=device)\n            y = y.to(device=device)\n\n            scores = model(x)\n            _, predictions = scores.max(1)\n            num_correct += (predictions == y).sum()\n            num_samples += predictions.size(0)\n\n        print(\n            f\"Got {num_correct} / {num_samples} with accuracy {float(num_correct)/float(num_samples)*100:.2f}\"\n        )\n\n    model.train()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"check_accuracy(train_loader, model)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"check_accuracy(val_loader, model)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}