Skip to content

Updating the weights of Quantized models #4969

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 2 commits into from
Nov 21, 2021
Merged

Updating the weights of Quantized models #4969

merged 2 commits into from
Nov 21, 2021

Conversation

datumbox
Copy link
Contributor

@datumbox datumbox commented Nov 21, 2021 •
edited
Loading

Fixes partially #3995

python train_quantization.py --device cpu --test-only --weights ImageNet1K_FBGEMM_RefV2 --model resnet50
Test:  Acc@1 80.282 Acc@5 94.976

python train_quantization.py --device cpu --test-only --weights ImageNet1K_FBGEMM_RefV2 --model resnext101_32x8d
Test:  Acc@1 82.574 Acc@5 96.132

cc @bjuncek

@datumbox datumbox added module: models.quantization Issues related to the quantizable/quantized models prototype labels Nov 21, 2021
@facebook-github-bot
Copy link

facebook-github-bot commented Nov 21, 2021 •
edited
Loading

💊 CI failures summary and remediations

As of commit e372ea5 (more details on the Dr. CI page):

💚 💚 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.

Click here to manually regenerate this comment.

@datumbox datumbox force-pushed the prototype/quantized_model_weights branch 3 times, most recently from 5de8b04 to 7ad2936 Compare November 21, 2021 10:55
@datumbox datumbox force-pushed the prototype/quantized_model_weights branch from 7ad2936 to 63d13ca Compare November 21, 2021 12:12
prabhat00155
prabhat00155 approved these changes Nov 21, 2021
View reviewed changes
Copy link
Contributor

@prabhat00155 prabhat00155 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @datumbox!

@datumbox datumbox merged commit 34c8b54 into pytorch:main Nov 21, 2021
@datumbox datumbox deleted the prototype/quantized_model_weights branch November 21, 2021 21:35
@datumbox datumbox linked an issue Nov 22, 2021 that may be closed by this pull request
Improve the accuracy of Classification models by using SOTA recipes and primitives #3995
Closed
facebook-github-bot pushed a commit that referenced this pull request Nov 30, 2021
@prabhat00155 @facebook-github-bot
[fbsync] Adding new Quantized models. (#4969)
3003dff 
Reviewed By: NicolasHug

Differential Revision: D32694325

fbshipit-source-id: ee2e725d41ee9256a97f86bfe4bd39e5012f7648
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@prabhat00155 prabhat00155 prabhat00155 approved these changes

Assignees
No one assigned
Labels
ciflow/default cla signed enhancement module: models.quantization Issues related to the quantizable/quantized models prototype
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Improve the accuracy of Classification models by using SOTA recipes and primitives
3 participants
@datumbox @facebook-github-bot @prabhat00155