Python 断言{'；theano'；，&'；tensorflow'；}断言错误中的&#u后端

我正在尝试运行，但出现以下错误：

Traceback (most recent call last):
  File "classifier_from_little_data_script_3.py", line 39, in <module>
    from keras import applications
  File "C:\Python35\lib\site-packages\keras\__init__.py", line 3, in <module>
    from . import activations
  File "C:\Python35\lib\site-packages\keras\activations.py", line 3, in <module>
    from . import backend as K
  File "C:\Python35\lib\site-packages\keras\backend\__init__.py", line 36, in <module>
    assert _backend in {'theano', 'tensorflow'}
AssertionError

ValueError: The shape of the input to "Flatten" is not fully defined (got (None, None, 512). Make sure to pass a complete "input_shape" or "batch_input_shape" argument to the first layer in your model.

编辑2

我已将后端更改为

tensorflow

，但出现以下错误：

Traceback (most recent call last):
  File "classifier_from_little_data_script_3.py", line 39, in <module>
    from keras import applications
  File "C:\Python35\lib\site-packages\keras\__init__.py", line 3, in <module>
    from . import activations
  File "C:\Python35\lib\site-packages\keras\activations.py", line 3, in <module>
    from . import backend as K
  File "C:\Python35\lib\site-packages\keras\backend\__init__.py", line 36, in <module>
    assert _backend in {'theano', 'tensorflow'}
AssertionError

ValueError: The shape of the input to "Flatten" is not fully defined (got (None, None, 512). Make sure to pass a complete "input_shape" or "batch_input_shape" argument to the first layer in your model.

我为第二次编辑添加了一个单独的问题

---

谢谢。

您的keras.json应该是这样的

{
    "image_data_format": "channels_last",
    "epsilon": 1e-07,
    "floatx": "float32",
    "backend": "tensorflow" 
}

---

请注意

“后端”：“tensorflow”

与您的

“后端”：“tf”

您能打印出您的

keras.json

文件吗？@MarcinMożejko感谢您的回复。当然，请参见问题中的编辑1，因此您应该将

tf

更改为

tensorflow

。@MarcinMożejko请参见我问题中的编辑2，了解将后端更改为“tensorflow”时出现的错误。谢谢。谢谢你友好的回复。当我将后端更改为“tensorflow”时，请参见问题中的编辑2。谢谢。我看到了编辑，但我建议接受这个答案，然后打开另一个包含新错误详细信息的问题。是的，当然。我接受了答案，并在此处添加了一个新问题：。谢谢你的支持