Keras: Is there any way to make convolutional model support zero masking?

[jinfengr]

I used zero masking in the word embedding layer, but encountered an error when stacking convolutional model on it. I saw a long thread discussing this feature in here but still not solved:
https://github.com/fchollet/keras/issues/411

I am wondering if there is any way to make convolutional model support zero masking?

Thanks!

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed after 30 days if no further activity occurs, but feel free to re-open a closed issue if needed.