{"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":"!unzip -q \"/kaggle/input/dogs-vs-cats/train.zip\"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!unzip -q \"/kaggle/input/dogs-vs-cats/test1.zip\"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# /train/cat.0.jpg\n# test1/1.jpg\n# !cd train/ && ls","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# importing modules\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\n\nfrom torch.utils.data import Dataset, DataLoader, ConcatDataset\nimport torch.nn as nn\nimport torch\nimport cv2\nimport torchvision\nfrom torchvision import transforms\n\nfrom PIL import Image\n\nimport numpy as np\nimport pandas as pd\n\nimport os\n\n%matplotlib inline\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device = 'cuda'","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img = mpimg.imread('./train/cat.0.jpg')\nimgplot = plt.imshow(img)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img = mpimg.imread('test1/1.jpg')\nimgplot = plt.imshow(img)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_dir = \"./train/\"\ntest_dir = \"./test1/\"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# list of all inputs\ntrain_files = os.listdir(train_dir)\ntest_files = os.listdir(test_dir)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class CustomDataset(Dataset):\n    def __init__(self, file_list, dir, mode='train', transform=None):\n        self.file_list = file_list\n        self.dir = dir\n        self.mode = mode\n        self.transform = transform\n        if self.mode == \"train\":\n            if 'dog' in self.file_list[0]:\n                self.label = 1\n            else:\n                self.label = 0\n        \n    def __len__(self):\n        return len(self.file_list)\n    \n    def __getitem__(self, idx):\n        img = Image.open(os.path.join(self.dir, self.file_list[idx])) # returns <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=500x374 at 0x7F656A1B88D0>\n        if self.transform:\n            img = self.transform(img)\n        \n        img = np.asarray(img)\n        if self.mode == 'train':\n            return img.astype('float32'), self.label\n        else:\n            return img.astype('float32'), self.file_list[idx]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"custom_dataset = CustomDataset(train_files, train_dir)\nprint(custom_dataset.__getitem__(0))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# transform data\ndata_transform = transforms.Compose([\n    transforms.Resize(256),\n    transforms.ColorJitter(),\n    transforms.RandomCrop(224),\n    transforms.RandomHorizontalFlip(),\n    transforms.Resize(128),\n    transforms.ToTensor()\n])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat_files = [tf for tf in train_files if 'cat' in tf]\ndog_files = [tf for tf in train_files if 'dog' in tf]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cats = CustomDataset(cat_files, train_dir, transform = data_transform)\ndogs = CustomDataset(dog_files, train_dir, transform = data_transform)\n\ncatdogs = ConcatDataset([cats, dogs])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataloader = DataLoader(catdogs, batch_size = 32, shuffle=True, num_workers=4)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"samples, labels = iter(dataloader).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)))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = torchvision.models.resnet18(pretrained=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"num_ftrs = model.fc.in_features\nnum_ftrs","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.classifier = nn.Sequential(\n    nn.Linear(num_ftrs, 500),\n    nn.Linear(500, 2)\n)\n\nmodel = model.to(device)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"criterion = nn.CrossEntropyLoss()\noptimizer = torch.optim.Adam(model.parameters(), lr=0.002, amsgrad=True)\nscheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=[500,1000,1500], gamma=0.5)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"epochs = 3\nitr = 1\np_itr = 200\nmodel.train()\ntotal_loss = 0\nloss_list = []\nacc_list = []\nfor epoch in range(epochs):\n    for samples, labels in dataloader:\n        samples, labels = samples.to(device), labels.to(device)\n        optimizer.zero_grad()\n        output = model(samples)\n        loss = criterion(output, labels)\n        loss.backward()\n        optimizer.step()\n        total_loss += loss.item()\n        scheduler.step()\n        \n        if itr%p_itr == 0:\n            pred = torch.argmax(output, dim=1)\n            correct = pred.eq(labels)\n            acc = torch.mean(correct.float())\n            print('[Epoch {}/{}] Iteration {} -> Train Loss: {:.4f}, Accuracy: {:.3f}'.format(epoch+1, epochs, itr, total_loss/p_itr, acc))\n            loss_list.append(total_loss/p_itr)\n            acc_list.append(acc)\n            total_loss = 0\n            \n        itr += 1\n\nplt.plot(loss_list, label='loss')\nplt.plot(acc_list, label='accuracy')\nplt.legend()\nplt.title('training loss and accuracy')\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"filename_pth = 'ckpt_resnet18_catdog.pth'\ntorch.save(model.state_dict(), filename_pth)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# doing for test dataset","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_transform = transforms.Compose([\n    transforms.Resize((128,128)),\n    transforms.ToTensor()\n])\n\ntestset = CustomDataset(test_files, test_dir, mode='test', transform = test_transform)\ntestloader = DataLoader(testset, batch_size = 32, shuffle=False, num_workers=4)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.eval()\nfn_list = []\npred_list = []\nfor x, fn in testloader:\n    with torch.no_grad():\n        x = x.to(device)\n        output = model(x)\n        pred = torch.argmax(output, dim=1)\n        fn_list += [n[:-4] for n in fn]\n        pred_list += [p.item() for p in pred]\n\nsubmission = pd.DataFrame({\"id\":fn_list, \"label\":pred_list})\nsubmission.to_csv('preds_resnet18.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"samples, _ = iter(testloader).next()\nsamples = samples.to(device)\nfig = plt.figure(figsize=(24, 16))\nfig.tight_layout()\noutput = model(samples[:24])\npred = torch.argmax(output, dim=1)\npred = [p.item() for p in pred]\nad = {0:'cat', 1:'dog'}\nfor num, sample in enumerate(samples[:24]):\n    plt.subplot(4,6,num+1)\n    plt.title(ad[pred[num]])\n    plt.axis('off')\n    sample = sample.cpu().numpy()\n    plt.imshow(np.transpose(sample, (1,2,0)))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}