报错AttributeError: ‘InputLayer‘ object has no attribute ‘outbound_nodes‘

环境：tensorflow 1.13.1+keras 2.2.4
在运行代码时出现报错如下：

File "F:\python tensorflow\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 584, in __call__
    inputs, outputs, args, kwargs)
  File "F:\python tensorflow\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 1416, in _set_connectivity_metadata_
    input_tensors=inputs, output_tensors=outputs, arguments=kwargs)
  File "F:\python tensorflow\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 1524, in _add_inbound_node
    arguments=arguments)
  File "F:\python tensorflow\Anaconda\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 1742, in __init__
    layer.outbound_nodes.append(self)
AttributeError: 'InputLayer' object has no attribute 'outbound_nodes'

通过百度查找发现问题是Keras 2.2.0进行了一些重构，而tf.keras尚未更新到该新API。'outbound_nodes’属性为在Keras 2.2.0中重命名为" _outbound_nodes"。
解决办法：找到最后报错文件的位置，将‘outbound_nodes’修改为‘_outbound_nodes’即可修复。
亲测有效！！！