Skip to content

Add regnet model from SWAG#5722

Merged
datumbox merged 5 commits intomainfrom
add-regnet-16-32-swag
Apr 1, 2022
Merged

Add regnet model from SWAG#5722
datumbox merged 5 commits intomainfrom
add-regnet-16-32-swag

Conversation

@YosuaMichael
Copy link
Copy Markdown
Contributor

@YosuaMichael YosuaMichael commented Apr 1, 2022

subtask of #5708

Adding weight of regnet_y_16gf and regnet_y_32gf model from https://github.com/facebookresearch/SWAG

@YosuaMichael YosuaMichael self-assigned this Apr 1, 2022
@facebook-github-bot
Copy link
Copy Markdown
Contributor

facebook-github-bot commented Apr 1, 2022 •
edited
Loading

💊 CI failures summary and remediations

As of commit 9904358 (more details on the Dr. CI page):

✅ None of the CI failures appear to be your fault 💚

🚧 2 ongoing upstream failures:

These were probably caused by upstream breakages that are not fixed 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.

@YosuaMichael YosuaMichael requested a review from datumbox April 1, 2022 16:24
@datumbox datumbox mentioned this pull request Apr 1, 2022
Closed
24 tasks
@YosuaMichael YosuaMichael marked this pull request as ready for review April 1, 2022 19:36
@YosuaMichael
Copy link
Copy Markdown
Contributor Author

YosuaMichael commented Apr 1, 2022

I run the test on imagenet1k val data with the following command:

# RegNet_Y_16GF_Weights.IMAGENET1K_SWAG_V1:
python -u ~/script/run_with_submitit.py --timeout 3000 --ngpus 1 --nodes 1 --partition train --model regnet_y_16gf --data-path="/datasets01_ontap/imagenet_full_size/061417" --test-only --batch-size=1 --weights="RegNet_Y_16GF_Weights.IMAGENET1K_SWAG_V1"
# Acc@1 86.012 Acc@5 98.054

#RegNet_Y_32GF_Weights.IMAGENET1K_SWAG_V1
python -u ~/script/run_with_submitit.py --timeout 3000 --ngpus 1 --nodes 1 --partition train --model regnet_y_32gf --data-path="/datasets01_ontap/imagenet_full_size/061417" --test-only --batch-size=1 --weights="RegNet_Y_32GF_Weights.IMAGENET1K_SWAG_V1"
# Acc@1 86.838 Acc@5 98.362

datumbox
datumbox approved these changes Apr 1, 2022
View reviewed changes
Copy link
Copy Markdown
Contributor

@datumbox datumbox left a comment

Choose a reason for hiding this comment

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

LGTM, thanks!

@datumbox datumbox merged commit 316c382 into main Apr 1, 2022
@datumbox datumbox deleted the add-regnet-16-32-swag branch April 1, 2022 20:47
@datumbox datumbox linked an issue Apr 1, 2022 that may be closed by this pull request
Add the SWAG pre-trained weights in TorchVision #5708
Closed
@datumbox datumbox mentioned this pull request Apr 4, 2022
Merged
facebook-github-bot pushed a commit that referenced this pull request Apr 6, 2022
@datumbox @facebook-github-bot
[fbsync] Add regnet model from SWAG (#5722)
c53f5b7 
Summary:
* Add regnet_y_16gf and regnet_y_32gf from swag

* Format with ufmt

* Add the experiment accuracy

Reviewed By: NicolasHug

Differential Revision: D35393157

fbshipit-source-id: 81a26e937296567eca829c25b31026a9662b7d16

Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
@datumbox datumbox mentioned this pull request Jul 27, 2022
Open
16 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

1 more reviewer

@datumbox datumbox datumbox approved these changes

Reviewers whose approvals may not affect merge requirements

Assignees

@YosuaMichael YosuaMichael

Labels

cla signed module: models new feature

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Add the SWAG pre-trained weights in TorchVision

3 participants

@YosuaMichael @facebook-github-bot @datumbox