added .eval() to HuggingfaceSubject #222
Open
Conversation
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
enabled evaluation mode for HF models before passing stimuli. This disables dropout and changes normalisation layers (e.g. BatchNorm) to use averages computed during training
mschrimpf
approved these changes
May 31, 2024
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Outdated suggestions cannot be applied.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.
Enabled evaluation mode for HF models before passing stimuli. This disables dropout and changes normalisation layers (e.g. BatchNorm) to use averages computed during training. I computed brain alignment with and without
.eval()and the results are different!In the future there needs to be a
_PytorchTransformerWrapperlike here to enable eval for any PyTorch model and not only HF models: https://github.com/mschrimpf/neural-nlp/blob/6e1a989b24fff0ffd7cac67d880a94136c4b4fb5/neural_nlp/models/implementations.py#L686