[Fix] : Correct Softmax Gradient #31
Merged
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
- This is no fix afterall...but yeah it looks good now, dont judge my career on the basis of this commit later on :(
Contributor
Author
|
@PrimedErwin |
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Outdated suggestions cannot be applied.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.
This PR fixes a tricky bug in our softmax backwards pass, where the gradients weren't matching up with PyTorch Results.
Fixed GradFn_softmax to ensure it correctly computes the full Jacobian-vector product and Tensor_backward to recognise "Softmax" as a special case. Now, it knows to use the gradient from GradFn_softmax directly, skipping the extra multiplication