{"cells":[{"metadata":{},"cell_type":"markdown","source":"Dataset available here: https://www.kaggle.com/xhlulu/panda-resized-train-data-512x512"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport openslide\nimport matplotlib.pyplot as plt\nfrom PIL import Image\nimport cv2\nfrom tqdm.notebook import tqdm\nimport skimage.io\nfrom skimage.transform import resize, rescale","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Load dataframe"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_labels = pd.read_csv('/kaggle/input/prostate-cancer-grade-assessment/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_labels.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_dir = '/kaggle/input/prostate-cancer-grade-assessment/train_images/'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mask_dir = '/kaggle/input/prostate-cancer-grade-assessment/train_label_masks/'\nmask_files = os.listdir(mask_dir)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Speed tests"},{"metadata":{"trusted":true},"cell_type":"code","source":"img_id = train_labels.image_id[0]\npath = data_dir + img_id + '.tiff'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%time biopsy = openslide.OpenSlide(path)\n%time biopsy2 = skimage.io.MultiImage(path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%timeit img = biopsy.get_thumbnail(size=(512, 512))\n%timeit out = resize(biopsy2[-1], (512, 512))\n%timeit out = cv2.resize(biopsy2[-1], (512, 512))\n%timeit out = Image.fromarray(biopsy2[-1]).resize((512, 512))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"out = cv2.resize(biopsy2[-1], (512, 512))\n\n%timeit Image.fromarray(out).save(img_id+'.png')\n%timeit cv2.imwrite(img_id+'.png', out)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Conclusion: skimage is fastest for loading, cv2 is fastest for resizing and saving."},{"metadata":{},"cell_type":"markdown","source":"### Try loading masks"},{"metadata":{"trusted":true},"cell_type":"code","source":"mask = skimage.io.MultiImage(mask_dir + mask_files[1])\nimg = skimage.io.MultiImage(data_dir + mask_files[1].replace(\"_mask\", \"\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mask[-1].shape, img[-1].shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Start here"},{"metadata":{"trusted":true},"cell_type":"code","source":"save_dir = \"/kaggle/train_images/\"\nos.makedirs(save_dir, exist_ok=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for img_id in tqdm(train_labels.image_id):\n    load_path = data_dir + img_id + '.tiff'\n    save_path = save_dir + img_id + '.png'\n    \n    biopsy = skimage.io.MultiImage(load_path)\n    img = cv2.resize(biopsy[-1], (512, 512))\n    cv2.imwrite(save_path, img)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"save_mask_dir = '/kaggle/train_label_masks/'\nos.makedirs(save_mask_dir, exist_ok=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for mask_file in tqdm(mask_files):\n    load_path = mask_dir + mask_file\n    save_path = save_mask_dir + mask_file.replace('.tiff', '.png')\n    \n    mask = skimage.io.MultiImage(load_path)\n    img = cv2.resize(mask[-1], (512, 512))\n    cv2.imwrite(save_path, img)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!tar -czf train_images.tar.gz ../train_images/*.png\n!tar -czf train_label_masks.tar.gz ../train_label_masks/*.png","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}