preprocess_images.py 文件源码

def preprocess_images_multiprocess(path2dataset_orig, prefix_orig, path2dataset_dest, prefix_dest, img_rows, img_cols, img_crop_rows, img_crop_cols):
    # Origin path = prefix + path -> /mnt/img/img393.JPEG
    # Destiny path = prefix2 + path -> /mnt/h5/img393.h5


    with open(path2dataset_orig, 'rb') as fin:
        paths = fin.readlines()

    num_total_paths = len(paths)

    num_cores = multiprocessing.cpu_count()
    processed_paths = Parallel(n_jobs=num_cores)(delayed(preprocess_images_worker) \
                                                     (line,  prefix_orig, prefix_dest, img_rows, img_cols, img_crop_rows, img_crop_cols) for line in paths)
    processed_paths = [elem for elem in processed_paths if elem]

    with open(path2dataset_dest, "wb") as fout:
        fout.writelines(processed_paths)

    print("Total images pre-processed: %d (remember that corrupted or not present images were discarded)" % len(processed_paths))