Ошибка тензорного потока: сообщение протокола ConvolutionalBoxPredictor не имеет поля box_encodings_clip_range

Question

Я новичок в Tensorflow и пробую простой учебник по обучению переносу: https://tensorflow -object-detection-api-tutorial.readthedocs.io / en / latest / training.html .

Когда я пытаюсь начать тренировку с помощью команды:

python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/ssd_mobilenet_v2_coco.config

Я получаю ошибку ниже:

WARNING: The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
  * https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
  * https://github.com/tensorflow/addons
If you depend on functionality not listed there, please file an issue.

WARNING:tensorflow:From /home/USER/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py:125: main (from __main__) is deprecated and will be removed in a future version.
Instructions for updating:
Use object_detection/model_main.py.
Traceback (most recent call last):
  File "train.py", line 184, in <module>
    tf.app.run()
  File "/home/USER/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
    _sys.exit(main(argv))
  File "/home/USER/.local/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func
    return func(*args, **kwargs)
  File "train.py", line 180, in main
    graph_hook_fn=graph_rewriter_fn)
  File "/home/USER/AI_Workspace/models/research/object_detection/legacy/trainer.py", line 249, in train
    detection_model = create_model_fn()
  File "/home/USER/AI_Workspace/models/research/object_detection/builders/model_builder.py", line 132, in build
    return _build_ssd_model(model_config.ssd, is_training, add_summaries)
  File "/home/USER/AI_Workspace/models/research/object_detection/builders/model_builder.py", line 279, in _build_ssd_model
    num_classes, ssd_config.add_background_class)
  File "/home/USER/AI_Workspace/models/research/object_detection/builders/box_predictor_builder.py", line 690, in build
    if config_box_predictor.HasField('box_encodings_clip_range'):
ValueError: Protocol message ConvolutionalBoxPredictor has no field box_encodings_clip_range.

Понятия не имею, что это значит. Кто-нибудь знает, что это такое и что может быть причиной?