run_evaluations.py 文件源码

def main():
  HASH_IMG_NAME = True
  pylab.rcParams['figure.figsize'] = (10.0, 8.0)
  json.encoder.FLOAT_REPR = lambda o: format(o, '.3f')

  parser = argparse.ArgumentParser()
  parser.add_argument("-i", "--inputfile", type=str, required=True,
      help='File containing model-generated/hypothesis sentences.')
  parser.add_argument("-r", "--references", type=str, required=True,
      help='JSON File containing references/groundtruth sentences.')
  args = parser.parse_args()
  prediction_file = args.inputfile
  reference_file = args.references
  json_predictions_file = '{0}.json'.format(prediction_file)

  crf = CocoResFormat()
  crf.read_file(prediction_file, HASH_IMG_NAME)
  crf.dump_json(json_predictions_file)

  # create coco object and cocoRes object.
  coco = COCO(reference_file)
  cocoRes = coco.loadRes(json_predictions_file)

  # create cocoEval object.
  cocoEval = COCOEvalCap(coco, cocoRes)

  # evaluate results
  cocoEval.evaluate()

  # print output evaluation scores
  for metric, score in cocoEval.eval.items():
    print '%s: %.3f'%(metric, score)