Skip to content

Add MaskRCNN improved weights#5773

Merged
datumbox merged 3 commits intopytorch:mainfrom
datumbox:models/maskrcnn
Apr 6, 2022
Merged

Add MaskRCNN improved weights#5773
datumbox merged 3 commits intopytorch:mainfrom
datumbox:models/maskrcnn

Conversation

@datumbox
Copy link
Copy Markdown
Contributor

@datumbox datumbox commented Apr 6, 2022 •
edited
Loading

Fixes #5307

Adds new pre-trained weights for MaskRCNN + ResNet50 + FPN for the v2 variant with post-paper optimizations (no FrozenBN + c5 instead of p5 input on extra layers + heavier RPN/Box/Mask Heads with BNs). It improves the previous baseline by +9.5 mAP for boxes and +7.2 mAP for masks.

Trained with:

python -u run_with_submitit.py --ngpus 8 --nodes 4 --dataset coco --model maskrcnn_resnet50_fpn_v2 \
--epochs 400 --lr-steps 352 384 --lr 0.1 --batch-size 2 --weight-decay 0.00004 --sync-bn \
--data-augmentation lsj

Verified with:

torchrun --nproc_per_node=1 train.py --test-only --weights MaskRCNN_ResNet50_FPN_V2_Weights.COCO_V1 \
--model maskrcnn_resnet50_fpn_v2 -b 1

IoU metric: bbox
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.474
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.679
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.518
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.308
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.512
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.609
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.367
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.589
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.618
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.443
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.652
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.762
IoU metric: segm
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.418
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.651
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.450
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.222
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.447
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.602
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.337
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.527
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.551
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.363
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.587
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.715

@datumbox datumbox marked this pull request as draft April 6, 2022 14:36
This was referenced Apr 6, 2022
Merged
Closed
Closed
@datumbox datumbox requested a review from YosuaMichael April 6, 2022 14:55
@datumbox datumbox marked this pull request as ready for review April 6, 2022 14:55
YosuaMichael
YosuaMichael approved these changes Apr 6, 2022
View reviewed changes
Copy link
Copy Markdown
Contributor

@YosuaMichael YosuaMichael left a comment

Choose a reason for hiding this comment

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

LGTM!

@datumbox datumbox merged commit bc9924f into pytorch:main Apr 6, 2022
@datumbox datumbox deleted the models/maskrcnn branch April 6, 2022 16:28
facebook-github-bot pushed a commit that referenced this pull request May 5, 2022
@YosuaMichael @facebook-github-bot
[fbsync] Add MaskRCNN improved weights (#5773)
a02d310 
Summary:
* Add MaskRCNN improved weights

* Adding recipe URL

(Note: this ignores all push blocking failures!)

Reviewed By: jdsgomes, NicolasHug

Differential Revision: D36095710

fbshipit-source-id: ad917bbd12f545f62681bb4607b74b2ebe650592
@datumbox datumbox mentioned this pull request Jul 27, 2022
Open
16 tasks
@dscho15
Copy link
Copy Markdown

dscho15 commented Aug 29, 2022

Hey, where can i find the augmentations used for training this model?

@NicolasHug
Copy link
Copy Markdown
Member

NicolasHug commented Aug 30, 2022

@dscho15 The model was trained with the command above in #5773 (comment). It refers to these scripts, where you'll find the corresponding code https://github.com/pytorch/vision/tree/main/references/detection

@medphisiker medphisiker mentioned this pull request Jan 19, 2023
Open
2 tasks
@GeorgePearse GeorgePearse mentioned this pull request Oct 21, 2025
Open
2 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

1 more reviewer

@YosuaMichael YosuaMichael YosuaMichael approved these changes

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

cla signed module: models new feature topic: object detection

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Improve the accuracy of Detection & Segmentation models by using SOTA recipes and primitives

5 participants

@datumbox @dscho15 @NicolasHug @YosuaMichael @facebook-github-bot