Zero_infinity option for ctc loss #4415
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
When I implemented
ignore_nan_grad
for ctc modules of espnet2, pytorch-ctc didn't have the zero_infinity option.ignore_nan_grad
is not so efficient and looks complicated impelemetation, so I changed it to use thezero_infinity
option. (ESPnet1 already used it.)Note that this CTC class has both
ignore_nan_grad
andzero_infinity
options andignore_nan_grad
is an alias ofzero_infinity
. I leftignore_nan_grad
for backward compatiblity.