Remove torch.squeeze() step from the model's forward method. #659
Merged
Remove torch.squeeze() step from the model's forward method. #659
Conversation
Documentation previewhttps://nvidia-merlin.github.io/Transformers4Rec/review/pr-659 |
edknv
approved these changes
Mar 28, 2023
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
torch.squeeze()op inside the model's forward method is no longer needed.torch.squeeze()op was also raising an issue at inference when we pass a sequence with one element only. In fact, by callingtorch.squeeze()on all inputs we lose the information to separate between scalar features and list features with only one element. The new data loader is ensuring that list input with one element are kept as 2-D.torch.squeeze()op and added a check for applying the model on input sequences with one element, at inference.