[ao] Changed ratio of channels needed for input-weight rec #82795
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
Summary: After working on a tutorial and spending more time experimenting with the input-weight equalization recommendation feature, I realized that having half as the number of channels to benefit from input-weight was too high, and that it should be a bit more lenient. Based on the example I played around with in an internal tutorial, I found that somewhere in the 0.3 - 0.4 threshold made more sense. In the future, more in-depth testing and experimenting with more models may help further fine-tune this fraction of channels that would benefit. Test Plan: python test/test_quantization.py TestFxDetectInputWeightEqualization Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
This was referenced Aug 4, 2022
🔗 Helpful links
✅ No Failures (3 Pending)As of commit 6b05b9d (more details on the Dr. CI page): Expand to see more💚 💚 Looks good so far! There are no failures yet. 💚 💚 This comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
jerryzh168
approved these changes
Aug 5, 2022
vspenubarthi
added
release notes: quantization
|
@pytorchbot merge -g |
|
@pytorchbot successfully started a merge job. Check the current status here |
facebook-github-bot
pushed a commit
that referenced
this pull request
Aug 7, 2022
…82795) Summary: After working on a tutorial and spending more time experimenting with the input-weight equalization recommendation feature, I realized that having half as the number of channels to benefit from input-weight was too high, and that it should be a bit more lenient. Based on the example I played around with in an internal tutorial, I found that somewhere in the 0.3 - 0.4 threshold made more sense. In the future, more in-depth testing and experimenting with more models may help further fine-tune this fraction of channels that would benefit. Pull Request resolved: #82795 Approved by: https://github.com/jerryzh168 Test Plan: contbuild & OSS CI, see https://hud.pytorch.org/commit/pytorch/pytorch/5ca098fe3891f7151d73223c38e909aa9dd5c862 Test plan from GitHub: python test/test_quantization.py TestFxDetectInputWeightEqualization Reviewed By: kit1980 Differential Revision: D38478780 Pulled By: vspenubarthi fbshipit-source-id: 3e278dd5d3f821b031cf4193f31d28fd635b2850
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
Stack from ghstack (oldest at bottom):
Summary: After working on a tutorial and spending more time
experimenting with the input-weight equalization recommendation feature,
I realized that having half as the number of channels to benefit from
input-weight was too high, and that it should be a bit more lenient.
Based on the example I played around with in an internal tutorial, I
found that somewhere in the 0.3 - 0.4 threshold made more sense. In the
future, more in-depth testing and experimenting with more models may
help further fine-tune this fraction of channels that would benefit.
Test Plan: python test/test_quantization.py TestFxDetectInputWeightEqualization
Reviewers:
Subscribers:
Tasks:
Tags: