Batchnorm and masking
Open
- Dominant language
- Python
- Stars
- 939
- Forks
- 116
- PR merge metrics
- No merged PRs in 30d
Description
It looks like the batchnorm doesn't take into account the masking:
https://github.com/freewym/espresso/blob/6fca6cacd9d475d2676c527999e2d1bde08e7cbb/espresso/models/speech_tdnn.py#L170
Surely this isn't right?
However I don't know how to take it into account.
Contributor guide
Assessment
This issue has not been assessed yet.