Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixes for newer tensorflow version #24

Draft
wants to merge 8 commits into
base: main
Choose a base branch
from

Conversation

casabre
Copy link

@casabre casabre commented Jun 10, 2024

closes #23

@casabre
Copy link
Author

casabre commented Jun 10, 2024

@JesperDramsch maybe you can help. Do you know, why the Keras Layer does not have add_update during runtime?

...
           if self.center:
                update_list.append(K.moving_average_update(self.moving_mean, mu, self.momentum))
            if self.scale:
                update_list.append(K.moving_average_update(self.moving_Vrr, Vrr, self.momentum))
                update_list.append(K.moving_average_update(self.moving_Vii, Vii, self.momentum))
                update_list.append(K.moving_average_update(self.moving_Vri, Vri, self.momentum))
            self.add_update(update_list)
...

Finally, it is leading to

...
E       RuntimeError: Exception encountered when calling ComplexBatchNormalization.call().
E       
E       Could not automatically infer the output shape / dtype of 'complex_batch_normalization' (of type ComplexBatchNormalization). Either the `ComplexBatchNormalization.call()` method is incorrect, or you need to implement the `ComplexBatchNormalization.compute_output_spec() / compute_output_shape()` method. Error encountered:
E       
E       'ComplexBatchNormalization' object has no attribute 'add_update'
...

Any ideas? Because according to the documentation it seems to be there...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Using ComplexDense and ComplexConv now fails in Keras Sequential
1 participant