Input has undefined rank. Received: input_shape=<unknown>

[sleepingcat4]

trafficstars

Tensorflow Version: 2.9.2 Python Version: 3.7.15

Bug's Behaviour:

A bug happened! I have created a derived version of AlexNet, I think BatchNormalization layers might be the cuprit behind the error. As without BatchNormalization layer it works perfectly fine. 

I don't think it's relevant but I used some custom activation functions. with combination of "relu". Though those functions weren't that different from "relu" so, I don't expect any error. It'll be a great help, if someone can help me to solve this error :)

Relevant pointers and hints will also be appreciated!

Code that produces the error: # input_shape=(256, 256, 3) model.build(input_shape=(None, 220, 220, 3)) model.summary()

Relevant log output:

ValueError                                Traceback (most recent call last)
<ipython-input-16-a5158c5140ec> in <module>
      1 # input_shape=(256, 256, 3)
----> 2 model.build(input_shape=(None, 256, 256, 3))
      3 model.summary()

3 frames
/usr/local/lib/python3.7/dist-packages/keras/utils/tf_utils.py in validate_axis(axis, input_shape)
    241   if not rank:
    242     raise ValueError(
--> 243         f'Input has undefined rank. Received: input_shape={input_shape}')
    244 
    245   # Convert axis to list and resolve negatives

ValueError: Input has undefined rank. Received: input_shape=<unknown>

[sleepingcat4]

I was suggested to post this issue here from Tensorflow repo: https://github.com/tensorflow/tensorflow/issues/58211#issuecomment-1286514372

[tilakrayal]

@sleepingcat4, To expedite the trouble-shooting process, could you please provide a complete code and the TensorFlow version you are using. Thank you!

[google-ml-butler[bot]]

This issue has been automatically marked as stale because it has no recent activity. It will be closed if no further activity occurs. Thank you.

[google-ml-butler[bot]]

Closing as stale. Please reopen if you'd like to work on this further.