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

hub.KerasLayer is missing implementation of compute_output_shape() #596

Open
qlzh727 opened this issue May 19, 2020 · 1 comment
Open

hub.KerasLayer is missing implementation of compute_output_shape() #596

qlzh727 opened this issue May 19, 2020 · 1 comment

Comments

@qlzh727
Copy link
Member

@qlzh727 qlzh727 commented May 19, 2020

See tensorflow/tensorflow#39542 for more details.

Currently hub.KerasLayer is missing implementation of compute_output_shape(), which cause error when used with keras.layers.TimeDistributed

@eliorc
Copy link

@eliorc eliorc commented May 24, 2020

I've opened the original issue on tensorflow/tensorflow, the consequence of this missing implementation is that if you want to apply hub.KerasLayer over time using tf.keras.layers.TimeDistributed you can't as it will cause an error.

Since hub is used a lot for feature extraction from images, it is a very common use case as when working with a sequence of images (video/gifs etc.) you'll need to extract features over time

@gowthamkpr gowthamkpr assigned gowthamkpr and unassigned gowthamkpr May 27, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Linked pull requests

Successfully merging a pull request may close this issue.

None yet
3 participants
You can’t perform that action at this time.