files.py 文件源码

def _preload_files_single_volunteer(dataset_dir, speaker_id, view_id, utterance_types):

    all_videos = path.join(_current_path, 'splits/allVideos.txt')

    u_list = _gen_utterance_list(utterance_types)

    with open(all_videos, 'r') as f:
        contents = f.read().splitlines()

    video_list = [path.join(dataset_dir, line)
                  for line in contents
                  if 's' + str(speaker_id) + '_' in line
                  if 'v' + str(view_id) in line
                  if any(u in line for u in u_list)]

    from sklearn.model_selection import train_test_split
    train, test = train_test_split(video_list, test_size=0.30, random_state=0)

    return train, test