Implement GradFn_crossentropy and fix GradFn_softmax #8
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
Fix GradFn_softmax to index correctly and store only the vector jacobian product. Implement GradFn_crossentropy for proper backpropagation.
Numbers0689
changed the title
Numbers0689
force-pushed
the
fix-ctensor-prototype
branch
from
94d453a to
7616863
Compare
Numbers0689
changed the title
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Outdated suggestions cannot be applied.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.
Gradient Functions:
GradFn_crossentropyfor proper backpropagation, withoutGradFn_crossentropythe loss Tensor is disconnected from the rest of the computational graph.GradFn_softmaxto index correctly and store only the vector jacobian product. The existing function crashes the program as it tries to access out of range index, once the computational graph is connected (mentioned above) and the backward pass reaches this function.