Faster rcnn运行train.py报错：AssertionError: Duplicate registrations for type ‘optimizer‘

错误信息显示如下：

Traceback (most recent call last):
  File "D:/Pycharm/try/Bearing-fault-Diagnosis-based-on-deep-learning-main/Bearing-fault-Diagnosis-based-on-deep-learning-main/sign/cnn.py", line 3, in <module>
    from tensorflow import keras
  File "D:\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\__init__.py", line 473, in <module>
    keras._load()
  File "D:\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\util\lazy_loader.py", line 41, in _load
    module = importlib.import_module(self.__name__)
  File "D:\Anaconda\Anaconda\envs\tensorflow\lib\importlib\__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "D:\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\keras\__init__.py", line 25, in <module>
    from keras import models
  File "D:\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\keras\models\__init__.py", line 18, in <module>
    from keras.engine.functional import Functional
  File "D:\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\keras\engine\functional.py", line 25, in <module>
    from keras.engine import base_layer
  File "D:\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\keras\engine\base_layer.py", line 40, in <module>
    from keras.mixed_precision import loss_scale_optimizer
  File "D:\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\keras\mixed_precision\loss_scale_optimizer.py", line 20, in <module>
    from keras.optimizer_v2 import optimizer_v2
  File "D:\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\keras\optimizer_v2\optimizer_v2.py", line 1469, in <module>
    setter=RestoredOptimizer._set_hyper  # pylint: disable=protected-access
  File "D:\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\saved_model\revived_types.py", line 133, in register_revived_type
    raise AssertionError(f"Duplicate registrations for type '{identifier}'")

我的解决办法：

卸载掉keras即可正常运行，卸载语句如下：

pip uninstall keras -y 

成功解决！（我是在pytorch下运行的，在tensorflow中按此方法不知道能不能解决问题）