Layers.Flatten( ) fails under TF 2.16.1 but not under TF 2.15 about tensorflow HOT 6 CLOSED

Set the input_shape argument of your Dense layer equal to (sequence_length * raw_data.shape[-1],)

from tensorflow.

Hi @JuanVargas

I also encountered a similar error while training an image classification model.
Below is a list of measures that were effective in suppressing the error in my environment:

1. Use tf.ensure_shape to explicitly define the shape of tensors in the training and validation dataset.
   • Example: #57485 (comment)
2. Switch from graph execution to eager execution.
3. Use a reshape layer instead of a flatten layer.
   • In your case tf.keras.Reshape((sequence_length, raw_data.shape[-1])) or tf.keras.Reshape((None, sequence_length, raw_data.shape[-1]))

from tensorflow.

@JuanVargas
In order to expedite the trouble-shooting process, please provide a complete code snippet to reproduce the issue reported here. Thank you!

from tensorflow.

This issue is stale because it has been open for 7 days with no activity. It will be closed if no further activity occurs. Thank you.

from tensorflow.

This issue was closed because it has been inactive for 7 days since being marked as stale. Please reopen if you'd like to work on this further.

from tensorflow.

Are you satisfied with the resolution of your issue?
Yes
No

from tensorflow.