Refactored 'predict' function for BB torch models. #784
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
RobertSamoilescu
force-pushed
the
fix/prediction-function-torch
branch
from
126c346 to
c5a289f
Compare
Codecov Report
Additional details and impacted files@@ Coverage Diff @@
## master #784 +/- ##
=======================================
Coverage 75.72% 75.72%
=======================================
Files 72 72
Lines 8223 8223
=======================================
Hits 6227 6227
Misses 1996 1996
Flags with carried forward coverage won't be shown. Click here to find out more. |
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Outdated suggestions cannot be applied.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.
The refactoring ensures that the gradients are not computes and the model is in evaluation mode for torch models.
In the previous version, the
detachfunction was used. This means that the gradients were computed, but detached afterwards. Note that there is no need to compute the gradients at all as it adds extra computation complexity and memory consumption especially for large models. Furthermore we should try to emphasize the model should be inevalmode.