{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip /kaggle/input/dogs-vs-cats/test1.zip\n!unzip /kaggle/input/dogs-vs-cats/train.zip","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from __future__ import print_function\n\nimport glob\nfrom itertools import chain\nimport os\nimport random\nimport zipfile\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torch.optim as optim\nfrom PIL import Image\nfrom sklearn.model_selection import train_test_split\nfrom torch.optim.lr_scheduler import StepLR\nfrom torch.utils.data import DataLoader, Dataset\nfrom torchvision import datasets, transforms , models\nfrom tqdm.notebook import tqdm","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def seed_everything(seed):\n  random.seed(seed)\n  os.environ['PYTHONHASHSEED'] = str(seed)\n  np.random.seed(seed)\n  torch.manual_seed(seed)\n  torch.cuda.manual_seed(seed)\n  torch.cuda.manual_seed_all(seed)\n  torch.backends.cudnn.deterministic = True  ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"seed = 24\nseed_everything(seed)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#load data\ntrain_dir = './train'\ntest_dir = './test1'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from glob import glob\ntrain_list = glob(os.path.join(train_dir,'*'))\ntest_list = glob(os.path.join(test_dir,'*'))\nprint(f\"Num of train {len(train_list)}\")\nprint(f\"Num of test {len(test_list)}\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_labels = [path.split('/')[-1].split('.')[0] for path in train_list]\ntest_labels = [path.split('/')[-1].split('.')[0] for path in test_list]\nprint(len(train_labels),len(test_labels))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"count = 0\nfor it in train_labels:\n  if it =='cat':\n    count += 1\nprint(f\"num of cat {count}\")\nprint(f\"num of dog {len(train_labels) - count}\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#plot some image\nrandom_idx = np.random.randint(1, len(train_list),size=9)\nfig, axes = plt.subplots(3, 3, figsize=(7,5))\nfor idx, ax in enumerate(axes.ravel()):\n  img = Image.open(train_list[idx])\n  print(img.size)\n  ax.set_title(train_labels[idx])\n  ax.imshow(img)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#split data\nlist_train , list_valid = train_test_split(train_list, test_size = 0.2, stratify = train_labels,random_state=seed)\nprint(f'Num of train: {len(list_train)}')\nprint(f'Num of valid: {len(list_valid)}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Image augmentation\nimage_size = (224,224)\ntrain_transforms = transforms.Compose(\n    [\n     transforms.Resize(image_size),\n     transforms.RandomResizedCrop(image_size),\n     transforms.RandomHorizontalFlip(),\n     transforms.ToTensor(),\n    ]\n)\n\nvalid_transforms = transforms.Compose(\n    [\n     transforms.Resize(image_size),\n     transforms.RandomResizedCrop(image_size),\n     transforms.RandomHorizontalFlip(),\n     transforms.ToTensor(),\n    ]\n)\n\ntest_transforms = transforms.Compose(\n    [\n     transforms.Resize(image_size),\n     transforms.RandomResizedCrop(image_size),\n     transforms.RandomHorizontalFlip(),\n     transforms.ToTensor(),\n    ]\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#class Dataset\nclass CustomDataset(Dataset):\n    def __init__(self, file_list, transform=None):\n        self.file_list = file_list\n        self.transform = transform\n    \n    def __len__(self):\n        return len(self.file_list)\n    \n    def __getitem__(self, idx):\n        img_path = self.file_list[idx]\n        if img_path.split('/')[-1][-3:] == 'jpg':\n            img = Image.open(img_path)     \n            if self.transform is not None:\n                img_transform = self.transform(img)\n                label = img_path.split('/')[-1].split('.')[0]\n                label = 1 if label == 'dog' else 0\n        return img_transform, label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#class Dataset\nclass CustomDataset(Dataset):\n    def __init__(self, file_list, transform=None):\n        self.file_list = file_list\n        self.transform = transform\n    \n    def __len__(self):\n        return len(self.file_list)\n    \n    def __getitem__(self, idx):\n        img_path = self.file_list[idx]\n        if img_path.split('/')[-1][-3:] == 'jpg':\n            img = Image.open(img_path)     \n            if self.transform is not None:\n                img_transform = self.transform(img)\n                label = img_path.split('/')[-1].split('.')[0]\n                label = 1 if label == 'dog' else 0\n        return img_transform, label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = CustomDataset(list_train, transform=train_transforms)\nvalid_data = CustomDataset(list_valid, transform=valid_transforms)\ntest_data = CustomDataset(test_list, transform=test_transforms)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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=True)\ntest_loader = DataLoader(dataset=test_data, batch_size=batch_size, shuffle=True)\nprint(len(train_data),len(train_loader))\nprint(len(valid_data),len(valid_loader))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install efficientnet_pytorch","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from efficientnet_pytorch import EfficientNet\nmodel = EfficientNet.from_pretrained('efficientnet-b5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"num_feature = model._fc.in_features\nmodel.fc = nn.Linear(num_feature, 2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.to(device)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lr = 3e-5\ngamma = 0.2\n# loss function\ncriterion = nn.CrossEntropyLoss()\n# optimizer\noptimizer = optim.Adam(model.parameters(), lr=lr)\n# scheduler\nscheduler = StepLR(optimizer, step_size=1, gamma=gamma)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nepochs = 20\nfor epoch in range(epochs):\n    epoch_loss = 0\n    epoch_accuracy = 0\n\n    for data, label in tqdm(train_loader):\n        data = data.to(device)\n        label = label.to(device)\n\n        output = model(data)\n        loss = criterion(output, label)\n\n        optimizer.zero_grad()\n        loss.backward()\n        optimizer.step()\n\n        acc = (output.argmax(dim=1) == label).float().mean()\n        epoch_accuracy += acc / len(train_loader)\n        epoch_loss += loss / len(train_loader)\n\n    with torch.no_grad():\n        epoch_val_accuracy = 0\n        epoch_val_loss = 0\n        for data, label in valid_loader:\n            data = data.to(device)\n            label = label.to(device)\n\n            val_output = model(data)\n            val_loss = criterion(val_output, label)\n\n            acc = (val_output.argmax(dim=1) == label).float().mean()\n            epoch_val_accuracy += acc / len(valid_loader)\n            epoch_val_loss += val_loss / len(valid_loader)\n\n    print(\n        f\"Epoch : {epoch+1} - loss : {epoch_loss:.4f} - acc: {epoch_accuracy:.4f} - val_loss : {epoch_val_loss:.4f} - val_acc: {epoch_val_accuracy:.4f}\\n\"\n    )","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":{"trusted":true},"cell_type":"code","source":"","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":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","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}