Build gradient graph starting at the loss alone - #17240
Merged
baijumeswani merged 4 commits intoAug 24, 2023
Merged
Conversation
baijumeswani
added
the
training
pengwa
previously approved these changes
Aug 22, 2023
pengwa
left a comment
pengwa
left a comment
Contributor
There was a problem hiding this comment.
Should we add a comment here for explaination, or print something to users to let them be aware of this.
…baijumeswani/gradient-builder-from-loss-node-only
pengwa
approved these changes
Aug 24, 2023
baijumeswani
deleted the
baijumeswani/gradient-builder-from-loss-node-only
branch
August 24, 2023 06:54
Contributor
Author
|
Thank you for the review @pengwa :) |
Lafi7e
pushed a commit
that referenced
this pull request
Aug 28, 2023
snnn
pushed a commit
that referenced
this pull request
Aug 28, 2023
Cherry-pick 1st round for rel-1.16.0 from https://github.com/microsoft/onnxruntime/issues?q=label%3Arelease%3A1.16+label%3Atriage%3Aapproved+is%3Aclosed except #17201 because it caused UT failure and is not fixed yet. PR list: #16417 #16936 #17000 #17236 #17238 #17240 #17252 #17255 #17258 #17265 #17267 #17277
kleiti
pushed a commit
to kleiti/onnxruntime
that referenced
this pull request
Mar 22, 2024
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Previously, the training offline utility was building the gradient graph starting from all outputs of the onnx model.
Since the loss is already embedded in the model, it can be assumed that only the loss gradient is expected to be the starting point of the backward graph.
This pull request avoids building the gradient graph from all available graph outputs.