{"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":"markdown","source":"# Dogs vs. Cats VGG16 Fine Tuning","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"markdown","source":"## Import Libs","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport os, glob, time, copy, zipfile\nfrom PIL import Image\nfrom sklearn.model_selection import train_test_split\nfrom tqdm import tqdm\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\nimport torch.utils.data as data\nimport torch.nn.functional as F\nfrom torchvision import models, transforms","metadata":{"execution":{"iopub.status.busy":"2023-07-26T06:13:42.297696Z","iopub.execute_input":"2023-07-26T06:13:42.298090Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Setup Params","metadata":{}},{"cell_type":"code","source":"size = 224\nmean = (0.485, 0.456, 0.406)\nstd = (0.229, 0.224, 0.225)\nbatch_size = 32\ndevice = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\nnum_epoch = 10","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Unzip And Split Datasets","metadata":{}},{"cell_type":"code","source":"# init dataset dirs\n!rm -rf ../data","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# load and split dataset\nbase_dir = '../input/dogs-vs-cats-redux-kernels-edition'\ntrain_dir = '../data/train'\ntest_dir = '../data/test'\n\nos.makedirs('../data', exist_ok=True)\n\nwith zipfile.ZipFile(os.path.join(base_dir, 'train.zip')) as train_zip:\n    train_zip.extractall('../data')\n    \nwith zipfile.ZipFile(os.path.join(base_dir, 'test.zip')) as test_zip:\n    test_zip.extractall('../data')\n\n\ntrain_list = glob.glob(os.path.join(train_dir, '*.jpg'))\ntest_list = glob.glob(os.path.join(test_dir, '*.jpg'))\n\ntrain_list, val_list = train_test_split(train_list, test_size=0.1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Define Data Augmentation Tool ","metadata":{}},{"cell_type":"code","source":"class ImageTransform():\n    \n    def __init__(self, resize, mean, std):\n        self.data_transform = {\n            'train': transforms.Compose([\n                transforms.RandomResizedCrop(resize, scale=(0.5, 1.0)),\n                transforms.RandomHorizontalFlip(),\n                transforms.ToTensor(),\n                transforms.Normalize(mean, std)\n            ]),\n            'val': transforms.Compose([\n                transforms.Resize(256),\n                transforms.CenterCrop(resize),\n                transforms.ToTensor(),\n                transforms.Normalize(mean, std)\n            ])\n        }\n        \n    def __call__(self, img, phase):\n        return self.data_transform[phase](img)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Define Dataloader","metadata":{"execution":{"iopub.status.busy":"2023-07-26T00:58:35.105338Z","iopub.execute_input":"2023-07-26T00:58:35.105874Z","iopub.status.idle":"2023-07-26T00:58:35.133138Z","shell.execute_reply.started":"2023-07-26T00:58:35.105831Z","shell.execute_reply":"2023-07-26T00:58:35.131869Z"}}},{"cell_type":"code","source":"class ImageDataset(data.Dataset):\n    \n    def __init__(self, file_list, transform=None, phase='train'):    \n        self.file_list = file_list\n        self.transform = transform\n        self.phase = phase\n        \n    def __len__(self):\n        return len(self.file_list)\n    \n    def __getitem__(self, idx):\n        \n        img_path = self.file_list[idx]\n        img = Image.open(img_path)\n        \n        img_transformed = self.transform(img, self.phase)\n        \n        # Get Label\n        label = img_path.split('/')[-1].split('.')[0]\n        if label == 'dog':\n            label = 1\n        elif label == 'cat':\n            label = 0\n\n        return img_transformed, label","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Setup Dataset And Loader","metadata":{}},{"cell_type":"code","source":"# Dataset\ntrain_dataset = ImageDataset(train_list, transform=ImageTransform(size, mean, std), phase='train')\nval_dataset = ImageDataset(val_list, transform=ImageTransform(size, mean, std), phase='val')\n\n# DataLoader\ntrain_dataloader = data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)\nval_dataloader = data.DataLoader(val_dataset, batch_size=batch_size, shuffle=False)\n\ndataloader_dict = {'train': train_dataloader, 'val': val_dataloader}","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Load And Setup VGG16 Model","metadata":{}},{"cell_type":"code","source":"use_pretrained = True\nnet = models.vgg16(pretrained=use_pretrained)\nnet.classifier[6] = nn.Linear(in_features=4096, out_features=2)\n\nparams_to_update = []\n\nupdate_params_name = ['classifier.6.weight', 'classifier.6.bias']\n\nfor name, param in net.named_parameters():\n    if name in update_params_name:\n        param.requires_grad = True\n        params_to_update.append(param)\n    else:\n        param.requires_grad = False","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Define Train Function","metadata":{}},{"cell_type":"code","source":"criterion = nn.CrossEntropyLoss()\noptimizer = optim.Adam(params=params_to_update, lr=0.001)\n\ndef train_model(net, dataloader_dict, criterion, optimizer, num_epoch):\n    \n    since = time.time()\n    best_model_wts = copy.deepcopy(net.state_dict())\n    best_acc = 0.0\n    net = net.to(device)\n    print('training started')\n    for epoch in range(num_epoch):\n        print('Epoch {}/{}'.format(epoch + 1, num_epoch))\n        print('-'*20)\n        \n        for phase in ['train', 'val']:\n            \n            if phase == 'train':\n                net.train()\n            else:\n                net.eval()\n                \n            epoch_loss = 0.0\n            epoch_corrects = 0\n            \n            for inputs, labels in tqdm(dataloader_dict[phase]):\n                inputs = inputs.to(device)\n                labels = labels.to(device)\n                optimizer.zero_grad()\n                \n                with torch.set_grad_enabled(phase == 'train'):\n                    outputs = net(inputs)\n                    _, preds = torch.max(outputs, 1)\n                    loss = criterion(outputs, labels)\n                    \n                    if phase == 'train':\n                        loss.backward()\n                        optimizer.step()\n                        \n                    epoch_loss += loss.item() * inputs.size(0)\n                    epoch_corrects += torch.sum(preds == labels.data)\n                    \n            epoch_loss = epoch_loss / len(dataloader_dict[phase].dataset)\n            epoch_acc = epoch_corrects.double() / len(dataloader_dict[phase].dataset)\n            \n            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))\n            \n            # deep copy the model\n            if phase == 'val' and epoch_acc > best_acc:\n                best_acc = epoch_acc\n                best_model_wts = copy.deepcopy(net.state_dict())\n                \n    time_elapsed = time.time() - since\n    print('Training complete in {:.0f}m {:.0f}s'.format(\n        time_elapsed // 60, time_elapsed % 60))\n    print('Best val Acc: {:4f}'.format(best_acc))\n\n    # load best model weights\n    net.load_state_dict(best_model_wts)\n    return net","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Execute Training","metadata":{}},{"cell_type":"code","source":"net = train_model(net, dataloader_dict, criterion, optimizer, num_epoch)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Prediction And Create Submission Data","metadata":{}},{"cell_type":"code","source":"# Prediction\nid_list = []\npred_list = []\n\nwith torch.no_grad():\n    for test_path in tqdm(test_list):\n        img = Image.open(test_path)\n        _id = int(test_path.split('/')[-1].split('.')[0])\n\n        transform = ImageTransform(size, mean, std)\n        img = transform(img, phase='val')\n        img = img.unsqueeze(0)\n        img = img.to(device)\n\n        net.eval()\n\n        outputs = net(img)\n        preds = F.softmax(outputs, dim=1)[:, 1].tolist()\n        \n        id_list.append(_id)\n        pred_list.append(preds[0])\n    \n    \nres = pd.DataFrame({\n    'id': id_list,\n    'label': pred_list\n})\n\nres.sort_values(by='id', inplace=True)\nres.reset_index(drop=True, inplace=True)\n\nres.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}