Fix mask for RNN hidden states reset #28
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
kaixi287
changed the title
nikitardn
reviewed
Jun 17, 2024
| @@ -92,6 +92,8 @@ def forward(self, input, masks=None, hidden_states=None): | |||
| return out | |||
|
|
|||
| def reset(self, dones=None): | |||
| if dones is not None: | |||
| dones = dones.bool() | |||
There was a problem hiding this comment.
what happens if dones is None?
There was a problem hiding this comment.
All elements of hidden_state will be set to 0.0.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This PR updates the reset function to convert the
donesmask to a boolean mask before applying it to reset hidden states. Previously, the function used a 0/1 mask directly, which selected the first and second set of indices in the last but one dimension, rather than resetting the hidden states at the desired positions indicated by 1 in the mask. By converting thedonesmask to a boolean mask, we ensure that the hidden states are correctly reset at the specified positions.