src/dataset-generator/create_dataset_from_raw_csv.py [171:201]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                if os.path.isfile(source_file):
                    shutil.copy(source_file, output_dir)

    num_cores = multiprocessing.cpu_count()
    results = joblib.Parallel(n_jobs=num_cores, verbose=15)(joblib.delayed(process_image)(im_basename) for im_basename in im_basenames)

    # Check if we have all files for all images
    # We do this by making sure that we have the same number of files for each basename
    image_count = []
    for im_basename in pyprind.prog_bar(im_basenames):
        image_count.append(len(glob.glob(os.path.join(output_dir, im_basename + '*'))))
    max_count = np.max(image_count)
    failed_image_count = np.sum(np.array(image_count, int) != max_count)
    print("For each image, we should have {} files.".format(max_count)) 
    if failed_image_count > 0:
        print("{} images have less files.".format(failed_image_count))
        response = input("Shall we delete those non-complete images? [y/n]")
        while response.lower() not in ['y','n']:
            response = input("Please respond only with either 'Y' or 'N'. Try again: ")
        if response.lower() == 'y':
            for idx, im_basename in pyprind.prog_bar(list(enumerate(im_basenames))):
                if image_count[idx] < max_count:
                    for file_to_delete in glob.glob(os.path.join(output_dir, im_basename + '*')):
                        print('Deleting', file_to_delete)
                        os.remove(file_to_delete)

    print('Finished!')


if __name__ == '__main__':
    main()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/dataset-generator/create_dataset_from_updated_csv.py [169:201]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                if os.path.isfile(source_file):
                    shutil.copy(source_file, output_dir)

    num_cores = multiprocessing.cpu_count()
    results = joblib.Parallel(n_jobs=num_cores, verbose=15)(joblib.delayed(process_image)(im_basename) for im_basename in im_basenames)
    #for im_basename in im_basenames:
    #    process_image(im_basename) 

    # Check if we have all files for all images
    # We do this by making sure that we have the same number of files for each basename
    image_count = []
    for im_basename in pyprind.prog_bar(im_basenames):
        image_count.append(len(glob.glob(os.path.join(output_dir, im_basename + '*'))))
    max_count = np.max(image_count)
    failed_image_count = np.sum(np.array(image_count, int) != max_count)
    print("For each image, we should have {} files.".format(max_count)) 
    if failed_image_count > 0:
        print("{} images have less files.".format(failed_image_count))
        response = input("Shall we delete those non-complete images? [y/n]")
        while response.lower() not in ['y','n']:
            response = input("Please respond only with either 'Y' or 'N'. Try again: ")
        if response.lower() == 'y':
            for idx, im_basename in pyprind.prog_bar(list(enumerate(im_basenames))):
                if image_count[idx] < max_count:
                    for file_to_delete in glob.glob(os.path.join(output_dir, im_basename + '*')):
                        print('Deleting', file_to_delete)
                        os.remove(file_to_delete)

    print('Finished!')


if __name__ == '__main__':
    main()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -