运行export_inference_graph.py抛出值错误

Question

我是StackOverflow.I的新手，我正在尝试使用export_inference_graph.py导出一个模型。我使用faster_rcnn_inception_v2.I am在本地训练我的模型，并遵循这个教程。

在命令提示符中输入

python export_inference_graph.py --input_type image_tensor --pipeline_config_path CAPTCHA_training/faster_rcnn_inception_v2_coco.config --trained_checkpoint_prefix "CAPTCHA_training_dir/model.ckpt-51272" --output_directory CAPTCHA_inference_graph 

所有的路径都是正确的，我得到了跟随错误。

  File "export_inference_graph.py", line 206, in <module>
    tf.app.run()
  File "C:\Users\Jatin\anaconda3\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "C:\Users\Jatin\anaconda3\lib\site-packages\absl\app.py", line 303, in run
    _run_main(main, args)
  File "C:\Users\Jatin\anaconda3\lib\site-packages\absl\app.py", line 251, in _run_main
    sys.exit(main(argv))
  File "export_inference_graph.py", line 194, in main
    exporter.export_inference_graph(
  File "C:\Users\Jatin\anaconda3\lib\site-packages\object_detection\exporter.py", line 604, in export_inference_graph
    detection_model = model_builder.build(pipeline_config.model,
  File "C:\Users\Jatin\anaconda3\lib\site-packages\object_detection\builders\model_builder.py", line 1116, in build
    return build_func(getattr(model_config, meta_architecture), is_training,
  File "C:\Users\Jatin\anaconda3\lib\site-packages\object_detection\builders\model_builder.py", line 583, in _build_faster_rcnn_model
    _check_feature_extractor_exists(frcnn_config.feature_extractor.type)
  File "C:\Users\Jatin\anaconda3\lib\site-packages\object_detection\builders\model_builder.py", line 249, in _check_feature_extractor_exists
    raise ValueError('{} is not supported. See `model_builder.py` for features '
ValueError: faster_rcnn_inception_v2 is not supported. See `model_builder.py` for features extractors compatible with different versions of Tensorflow

我正在使用Python3.8.5和tensorflow 2.4.1版本，谢谢

Answer 1

根据错误看像是Tensorflow版本的问题。查看源faster_rcnn_inception_v2存在于if tf_version.is_tf1():下。试着用TF 1。

builder.py#L70

extractor.py#L33

faster_rcnn_inception_v2_coco存在于Tensorflow 1检测模型动物园。

models#共同训练的模型