貌似环境兼容问题

[XiHenSuper]

原始报错TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("Placeholder:0", shape=(3, 3, 3, 10), dtype=float32) is not an element of this graph.

加了```
from keras import backend as K
K.clear_session()

后报错：
`ValueError: Tensor("Placeholder:0", shape=(3, 3, 3, 10), dtype=float32) must be from the same graph as Tensor("conv1/kernel:0", shape=(3, 3, 3, 10), dtype=float32_ref).`

[bubbliiiing]

什么版本啊

[XiHenSuper]

tensorflow:1.13.1
keras:2.2.4

[bubbliiiing]

感觉好像没啥问题，你换成2.1.5看看，keras，如果还不行你截个图看看……

[XiHenSuper]

之前换成2.1.5仍然不行，
仍然报错：

ValueError: Tensor("Placeholder:0", shape=(3, 3, 3, 10), dtype=float32) must be from the same graph as Tensor("conv1/kernel:0", shape=(3, 3, 3, 10), dtype=float32_ref).

[bubbliiiing]

截图截图

[bubbliiiing]

真不合理