convert_features.py 文件源码

def main(unused_argv):

  print("tensorflow version: %s" % tf.__version__)

  all_frame_files = gfile.Glob(FLAGS.input_data_pattern)
  f_fullpath = all_frame_files[FLAGS.file_from : FLAGS.file_to]
  f_fns = [x.split('/')[-1] for x in f_fullpath]

  exist_files = gfile.Glob(FLAGS.output_path + "C*tfrecord")
  exist_fn = [x.split('/')[-1].replace('CAtr', 'Atr')  for x in exist_files]

  yet_2_split = [x for x,y in zip(f_fullpath, f_fns) if y not in exist_fn]

  vf = [FLAGS.output_path + 'C' + x.split('/')[-1] for x in yet_2_split]

  mylog('number of files suggested: %d'%len(f_fullpath))
  mylog('number of files yet to process: %d'%len(yet_2_split))

  if FLAGS.parallel:
    from concurrent import futures
    executor = futures.ProcessPoolExecutor(max_workers=2)
    executor.map(process_one_file, zip(yet_2_split, vf))
  else: 
    for filenames in zip(yet_2_split, vf):
        #mylog('processing: {}'.format(filenames))
        process_one_file(filenames)

  mylog("done")