深度学习_相关报错解决方案

1、AttributeError: module 'tensorflow.python.framework.ops' has no attribute '_TensorLike'

参考博客：

AttributeError: module ‘tensorflow.python.framework.ops‘ has no attribute ‘_TensorLike‘_module 'tensorflow.python.framework.ops' has no at-CSDN博客

问题：AttributeError: module ‘tensorflow.python.framework.ops‘ has no attribute ‘_TensorLike‘的解决方法_attributeerror: module 'tensorflow.python.framewor-CSDN博客

总结：装2.4.3版本的keras就可以

pip install keras==2.4.3

2、NotImplementedError: Cannot convert a symbolic Tensor (lstm/strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported

参考博客：

完美解决 NotImplementedError: Cannot convert a symbolic Tensor (sequential/gru/strided_slice:0) to a-CSDN博客 总结：安装numpy

pip install  numpy==1.19.1 -i https://pypi.tuna.tsinghua.edu.cn/simple

3、AttributeError: module 'tensorflow.compat.v2' has no attribute '__internal__'

参考博客：

AttributeError: module ‘tensorflow.compat.v2‘ has no attribute ‘__internal__‘_attributeerror: module 'tensorflow' has no attribu-CSDN博客

总结：

tensorflow 2.3.0，keras 2.3.1

pip install tensorflow==2.3.0
pip install keras==2.3.1