{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nimport time\nimport skimage.io\nimport numpy as np\nimport pandas as pd\nimport cv2\nimport PIL.Image\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torch.utils.data import DataLoader, Dataset\nfrom torch.utils.data.sampler import SubsetRandomSampler, RandomSampler, SequentialSampler\nimport albumentations\nfrom sklearn.model_selection import StratifiedKFold\nimport matplotlib.pyplot as plt\nfrom tqdm.notebook import tqdm\nimport zipfile\nimport torchvision\nimport shutil\nos.mkdir('output/')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Config","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"data_dir = '../input/prostate-cancer-grade-assessment'\ndf_train = pd.read_csv(os.path.join(data_dir, 'train.csv'))\nimage_folder = os.path.join(data_dir, 'train_images')\ntile_size = 256\nimage_size = 256\nn_tiles = 36\nnum_workers = 8\nprint(image_folder)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Create Folds","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"skf = StratifiedKFold(8, shuffle=True, random_state=42)\ndf_train['fold'] = -1\nfor i, (train_idx, valid_idx) in enumerate(skf.split(df_train, df_train['isup_grade'])):\n    df_train.loc[valid_idx, 'fold'] = i\ndf_train.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Dataset","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_tiles(img, mode=0):\n        result = []\n        h, w, c = img.shape\n        pad_h = (tile_size - h % tile_size) % tile_size + ((tile_size * mode) // 2)\n        pad_w = (tile_size - w % tile_size) % tile_size + ((tile_size * mode) // 2)\n\n        img2 = np.pad(img,[[pad_h // 2, pad_h - pad_h // 2], [pad_w // 2,pad_w - pad_w//2], [0,0]], constant_values=255)\n        img3 = img2.reshape(\n            img2.shape[0] // tile_size,\n            tile_size,\n            img2.shape[1] // tile_size,\n            tile_size,\n            3\n        )\n\n        img3 = img3.transpose(0,2,1,3,4).reshape(-1, tile_size, tile_size,3)\n        n_tiles_with_info = (img3.reshape(img3.shape[0],-1).sum(1) < tile_size ** 2 * 3 * 255).sum()\n        if len(img3) < n_tiles:\n            img3 = np.pad(img3,[[0,n_tiles-len(img3)],[0,0],[0,0],[0,0]], constant_values=255)\n        idxs = np.argsort(img3.reshape(img3.shape[0],-1).sum(-1))[:n_tiles]\n        img3 = img3[idxs]\n        for i in range(len(img3)):\n            result.append({'img':img3[i], 'idx':i})\n        return result, n_tiles_with_info >= n_tiles\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"transforms_train = albumentations.Compose([\n    albumentations.Transpose(p=0.5),\n    albumentations.VerticalFlip(p=0.5),\n    albumentations.HorizontalFlip(p=0.5),\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fold = 4\ndf_train = df_train[df_train['fold']<fold]\nindexes = np.arange(len(df_train))[:10]\nfor index in tqdm(indexes):\n    row = df_train.iloc[index]\n    img_id = row.image_id\n    tiff_file = os.path.join(image_folder, f'{img_id}.tiff')\n    image = skimage.io.MultiImage(tiff_file)[2]\n    tiles, OK = get_tiles(image, 0)\n    idxes = list(range(n_tiles))\n    n_row_tiles = int(np.sqrt(n_tiles))\n    images = np.zeros((image_size * n_row_tiles, image_size * n_row_tiles, 3))\n    for h in range(n_row_tiles):\n        for w in range(n_row_tiles):\n            i = h * n_row_tiles + w\n            if len(tiles) > idxes[i]:\n                this_img = tiles[idxes[i]]['img']\n            else:\n                this_img = np.ones((image_size, image_size, 3)).astype(np.uint8) * 255\n            this_img = transforms_train(image=this_img)['image']\n            h1 = h * image_size\n            w1 = w * image_size\n            images[h1:h1+image_size, w1:w1+image_size] = this_img\n    images = images.astype(np.float32)\n    images /= 255\n    plt.imsave('output/' + f'{img_id}.png', images)","execution_count":null,"outputs":[]},{"metadata":{"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}