AttributeError: module 'tensorflow' has no attribute 'reset_default_graph'

 

环境配置：
    python3.7
    tensorflow2.0
    Window 10

初始代码：
tf.reset_default_graph()

解决方法：
import tensorflow as tf
tf.compat.v1.reset_default_graph()

或者是这样：
import tensorflow.compat.v1 as tf
tf.reset_default_graph()

链接：https://blog.csdn.net/qq_43279647/article/details/105025034

 

 

File /home/software/anaconda3/envs/mydlenv/lib/python3.8/site-packages/keras/backend/tensorflow_backend.py:95, in clear_session()
     93 global _SESSION
     94 global _GRAPH_LEARNING_PHASES
---> 95 tf.reset_default_graph()
     96 reset_uids()
     97 _SESSION = None

AttributeError: module 'tensorflow' has no attribute 'reset_default_graph'

 

 

=============================

在：

import tensorflow as tf

处添加以下两句就可以了。

1.  
   from tensorflow.python.framework import ops
2.  
   ops.reset_default_graph()

    

    

    

    

   =============================

   This function is deprecated. Use tf.compat.v1.reset_default_graph() instead.

   Update This is not the only function to be out of date. Check out this answer for release notes and a conversion script.

    

    

   Change:

   import keras.<something>.<something>
   

   to:

   import tensorflow.keras.<something>.<something>
   

   Where 'something' is the module you want to import