{"cells":[{"metadata":{},"cell_type":"markdown","source":"### Import necessary libraries","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"\nimport os\nimport gc\nimport cv2\n\nimport numpy as np\nimport pandas as pd\nfrom joblib import delayed, Parallel\nfrom tqdm.notebook import tqdm, trange","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"N = 16\nH = 512\nW = 512\nC = cv2.COLOR_BGR2RGB","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Define paths and load .csv files","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"TEST_IMG_PATH = '../input/siim-isic-melanoma-classification/jpeg/test/'\nTRAIN_IMG_PATH = '../input/siim-isic-melanoma-classification/jpeg/train/'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')\ntrain_df = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Resize images to (512, 512) and save (with multi-threading)","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\ndef save_to_zip(out_path):\n    # ZIP & rm -rf (remove) folder\n\n    if 'test' in out_path:\n        !zip -r test.zip test\n        !rm -rf test\n\n    if 'train_1' in out_path:\n        !zip -r train_1.zip train_1\n        !rm -rf train_1\n\n    if 'train_2' in out_path:\n        !zip -r train_2.zip train_2\n        !rm -rf train_2\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def save(ids, in_path, out_path):\n    # Resize images to (512, 512) and save\n\n    ids = tqdm(ids)\n\n    for idx, image_name in enumerate(ids):\n        input_read_path = in_path + image_name\n        image = cv2.imread(input_read_path + '.jpg')\n        image = cv2.resize(cv2.cvtColor(image, C), (H, W))\n        output_write_path = out_path + image_name + '.jpg'\n        cv2.imwrite(output_write_path, image); del image; gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Create directories and image ID lists\n\n!mkdir test\n!mkdir train_1\n!mkdir train_2\n\nlength = int(0.5*len(train_df))\ntest_ids = np.array_split(np.array(test_df.image_name), N)\ntrain_ids_1 = np.array_split(np.array(train_df.image_name[:length]), N)\ntrain_ids_2 = np.array_split(np.array(train_df.image_name[length:]), N)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Save resized test images to folders with multi-threading\n\npath = \"test/\"\nparallel = Parallel(n_jobs=N, backend=\"threading\")\nparallel(delayed(save)(ids, TEST_IMG_PATH, path) for ids in test_ids)\n\n# Save resized train images to folders files with multi-threading\n\npath = \"train_1/\"\nparallel = Parallel(n_jobs=N, backend=\"threading\")\nparallel(delayed(save)(ids, TRAIN_IMG_PATH, path) for ids in train_ids_1)\n\npath = \"train_2/\"\nparallel = Parallel(n_jobs=N, backend=\"threading\")\nparallel(delayed(save)(ids, TRAIN_IMG_PATH, path) for ids in train_ids_2)","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}