{"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","execution":{"iopub.status.busy":"2022-12-02T14:24:55.823645Z","iopub.execute_input":"2022-12-02T14:24:55.824825Z","iopub.status.idle":"2022-12-02T14:24:55.857301Z","shell.execute_reply.started":"2022-12-02T14:24:55.824685Z","shell.execute_reply":"2022-12-02T14:24:55.855575Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import zipfile\n\nzip_files = ['test1', 'train']\n\nfor zip_file in zip_files:\n    with zipfile.ZipFile(\"../input/dogs-vs-cats/{}.zip\".format(zip_file),\"r\") as z:\n        z.extractall(\".\")\n        print(\"{} unzipped\".format(zip_file))","metadata":{"execution":{"iopub.status.busy":"2022-12-02T14:24:55.859067Z","iopub.execute_input":"2022-12-02T14:24:55.859428Z","iopub.status.idle":"2022-12-02T14:25:15.671247Z","shell.execute_reply.started":"2022-12-02T14:24:55.859397Z","shell.execute_reply":"2022-12-02T14:25:15.670012Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import torchvision.models as models\nfrom torchvision import transforms\nfrom torchvision.transforms import ToTensor, Resize\nfrom torch.utils.data import DataLoader,Dataset\nimport os\nimport numpy as np\nfrom PIL import  Image\nimport torch\nfrom tqdm import tqdm\nimport torch.nn as nn\nfrom torch import optim\nimport copy","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_path = \"../working/train\" \ntest_path = \"../working/test1\"\nbatch_size = 128\nepochs = 5\nlr = 1e-3\ndevice = \"cuda\" if torch.cuda.is_available() else \"cpu\"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model=models.resnet18(pretrained=True)\nfor param in model.parameters():\n    param.requires_grad = False\n    \nmodel.fc = nn.Sequential(*[\n    nn.Linear(in_features=512, out_features=2),\n    nn.Softmax(dim=1)\n])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"transformer=transforms.Compose([ToTensor(),Resize((500,500))])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class get_data(Dataset):\n\n    def __init__(self, train_dir, transform = None):\n        \n        self.train_dir = train_dir\n        self.transform = transform\n        self.images = os.listdir(train_dir) #os.listdir返回指定路径下的文件和文件夹列表\n        \n\n    def __len__(self):\n        return len(self.images)\n    \n    def __getitem__(self, index):\n        image_path = os.path.join(self.train_dir, self.images[index])\n        label = self.images[index].split(\".\")[0]\n\n        label = 0 if label == 'cat' else 1\n        \n        image = np.array(Image.open(image_path))\n        \n        if self.transform is not None:\n            image = self.transform(image)\n\n        return image, label","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = DataLoader(get_data(train_path,transformer), batch_size=batch_size)\ntest_data = DataLoader(get_data(test_path,transformer), batch_size=batch_size)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def test(model, data):\n\n    total = 0\n    correct = 0\n\n    for (images, labels) in data:\n        images = images.to(device)\n        x = model(images)\n        _, pred = torch.max(x, 1)\n        total += x.size(0)\n        correct += torch.sum(pred.to(device) == labels.to(device))\n\n    return correct*100/total","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def train(num_epoch = epochs, lr = lr, device = device):\n    accuracies = []\n    cnn = model.to(device)\n    cec = nn.CrossEntropyLoss()\n    optimizer = optim.Adam(cnn.parameters(), lr=lr)\n\n    max_accuracy = 0\n\n    for epoch in range(num_epoch):\n        for i, (images, labels) in tqdm(enumerate(train_data)):\n            images = images.to(device)\n            labels = labels.to(device)\n            optimizer.zero_grad()\n            pred = cnn(images)\n            loss = cec(pred, labels)\n            loss.backward()\n            optimizer.step()\n        accuracy = float(test(cnn,test_data))\n        accuracies.append(accuracy)\n        if accuracy > max_accuracy:\n            best_model = copy.deepcopy(cnn)\n            max_accuracy = accuracy\n            print(\"saving best model with accuracy: \", accuracy)\n        print(\"Epoch: \", epoch+1, \"Accuracy: \", accuracy, \"%\")\n\n    return best_model","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"resnet=train()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"torch.save(resnet.state_dict(), \"ResNet18_CatDog.pth\")","metadata":{},"execution_count":null,"outputs":[]}]}