Skip to content
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

Add regnet_y_128gf from SWAG #5732

Merged
merged 4 commits into from
Apr 4, 2022
Merged

Add regnet_y_128gf from SWAG #5732

merged 4 commits into from
Apr 4, 2022

Conversation

YosuaMichael
Copy link
Contributor

subtask of #5708

Adding weight of regnet_y_128gf model from https://github.com/facebookresearch/SWAG

@YosuaMichael YosuaMichael self-assigned this Apr 4, 2022
@facebook-github-bot
Copy link

facebook-github-bot commented Apr 4, 2022 •
edited
Loading

💊 CI failures summary and remediations

As of commit 5560105 (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.

@YosuaMichael YosuaMichael marked this pull request as draft April 4, 2022 11:12
@YosuaMichael YosuaMichael marked this pull request as ready for review April 4, 2022 12:28
@YosuaMichael
Copy link
Contributor Author

@datumbox since the regnet_y_128gf is already implemented before but it just have no weight, so in this implementation we just add the weight only.

@datumbox
Copy link
Contributor

datumbox commented Apr 4, 2022

@YosuaMichael Thanks, looking good! Could you provide the validation output similar to #5722 (comment)?

@YosuaMichael
Copy link
Contributor Author

@YosuaMichael Thanks, looking good! Could you provide the validation output similar to #5722 (comment)?

Ah yeah, I forgot to add this. Here it is:

python -u ~/script/run_with_submitit.py --timeout 3000 --ngpus 1 --nodes 1 --partition train --model regnet_y_128gf --data-path="/datasets01_ontap/imagenet_full_size/061417" --test-only --batch-size=1 --weights="RegNet_Y_128GF_Weights.IMAGENET1K_SWAG_V1"
# Test:  Total time: 0:26:48
# Test:  Acc@1 88.228 Acc@5 98.682

@YosuaMichael YosuaMichael merged commit a7746ef into main Apr 4, 2022
@datumbox datumbox deleted the add-regnet-128-swag branch April 4, 2022 16:19
@datumbox datumbox mentioned this pull request Apr 5, 2022
Closed
24 tasks
facebook-github-bot pushed a commit that referenced this pull request Apr 6, 2022
@datumbox @facebook-github-bot
[fbsync] Add regnet_y_128gf from SWAG (#5732)
ab524a8 
Summary:
* Add regnet_y_128gh_swag weight

* Add default weight for regnet_y_128gf

* Add the accuracy from experiments

Reviewed By: NicolasHug

Differential Revision: D35393169

fbshipit-source-id: 2086ec2a7310cc83b4a294403d7e380f3f338e50
@datumbox datumbox linked an issue Apr 10, 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 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

@datumbox datumbox datumbox approved these changes

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