[Algorithm] Support H2RBox #644

yangxue0827 · 2022-11-24T15:38:24Z

Motivation

Support weakly supervised oriented object detection algorithm H2Rbox in MMRotate 1.x
Support DOTA-v1.5 and DOTA-v2.0

Modification

Create h2rbox.py at detectors
Create h2rbox_head.py at dense_heads
Create DOTAv15Dataset and DOTAv2Dataset in dota.py
Create dotav15.py and dotav2.py at configs/base/datasets
Create h2rbox_consistency_loss.py at losses
Create README.md and metafile.yml at configs/h2rbox
Create h2rbox-le90_r50_fpn_adamw-1x_dota.py , h2rbox-le90_r50_fpn_adamw-3x_dota.py and h2rbox-le90_r50_fpn_adamw-1x_dota-ms.py at configs/h2rbox
Create h2rbox-le90_r50_fpn_adamw-1x_dotav15.py and h2rbox-le90_r50_fpn_adamw-3x_dotav15.py at configs/h2rbox/dotav15
Create h2rbox-le90_r50_fpn_adamw-1x_dotav2.py and h2rbox-le90_r50_fpn_adamw-3x_dotav2.py at configs/h2rbox/dotav2
Create h2rbox-le90_r50_fpn_adamw-1x_dior.py at configs/h2rbox/dior
Create test_h2rbox at test_detectors
Update test_loss.py at test_losses
Update test_dota.py at test_datasets
Update test_h2rbox_heads.py at test_dense_heads

Performance

Performance on DOTA1.0

This PR

Backbone	mAP	Angle	lr schd	Mem (GB)	Inf Time (fps)	MS	Batch Size	Configs
ResNet50 (1024,1024,200)	68.75	le90	1x	6.25		-	2	h2rbox-le90_r50_fpn_adamw-1x_dota
ResNet50 (1024,1024,200)	71.31	le90	3x	6.64		-	2	h2rbox-le90_r50_fpn_adamw-3x_dota
ResNet50 (1024,1024,200)	74.43	le90	1x	6.12	-	-	2	h2rbox-le90_r50_fpn_adamw-1x_dota-ms

Original PyTorch Implementation (Paper)

Backbone	mAP	Angle	lr schd	Mem (GB)	Inf Time (fps)	MS	Batch Size	Configs
ResNet50 (1024,1024,200)	67.45	le90	1x	7.02	28.5	-	2	h2rbox_r50_adamw_fpn_1x_dota_le90
ResNet50 (1024,1024,200)	70.77	le90	3x	7.02	28.5	-	2	h2rbox_r50_adamw_fpn_3x_dota_le90
ResNet50 (1024,1024,200)	74.40	le90	1x	8.58	-	-	2	h2rbox_r50_adamw_fpn_3x_dota_ms_le90

Jittor Implementation

Backbone	mAP	Angle	lr schd	MS	Batch Size	Configs
ResNet50 (1024,1024,200)	67.62	le135	1x	-	2	h2rbox_obb_r50_adamw_fpn_1x_dota

Performance on DOTA1.5

This PR

Backbone	mAP	Angle	lr schd	Mem (GB)	Inf Time (fps)	MS	Batch Size	Configs
ResNet50 (1024,1024,200)	60.33	le90	1x	6.83		-	2	h2rbox-le90_r50_fpn_adamw-1x_dotav15
ResNet50 (1024,1024,200)	62.65	le90	1x	6.34		-	2	h2rbox-le90_r50_fpn_adamw-3x_dotav15

Original PyTorch Implementation (Paper)

Backbone	mAP	Angle	lr schd	Mem (GB)	Inf Time (fps)	MS	Batch Size	Configs
ResNet50 (1024,1024,200)	60.19	le90	1x	10.68	25.8	-	2	h2rbox_r50_adamw_fpn_1x_dotav15_le90
ResNet50 (1024,1024,200)	62.60	le90	3x	10.68	25.8	-	2	h2rbox_r50_adamw_fpn_3x_dotav15_le90

Performance on DOTA2.0

This PR

Backbone	mAP	Angle	lr schd	Mem (GB)	Inf Time (fps)	MS	Batch Size	Configs
ResNet50 (1024,1024,200)	47.08	le90	1x	7.58		-	2	h2rbox-le90_r50_fpn_adamw-1x_dotav2
ResNet50 (1024,1024,200)	50.20	le90	1x	7.74		-	2	h2rbox-le90_r50_fpn_adamw-3x_dotav2

Original PyTorch Implementation (Paper)

Backbone	mAP	Angle	lr schd	Mem (GB)	Inf Time (fps)	MS	Batch Size	Configs
ResNet50 (1024,1024,200)	45.87	le90	1x	11.57	25.0	-	2	h2rbox_r50_adamw_fpn_1x_dotav2_le90
ResNet50 (1024,1024,200)	47.86	le90	3x	11.57	25.0	-	2	h2rbox_r50_adamw_fpn_3x_dotav2_le90

Performance on DIOR

This PR

Backbone	AP50:95	AP50	AP75	Angle	lr schd	Mem (GB)	Inf Time (fps)	MS	Batch Size	Configs
ResNet50 (1024,1024,200)	33.06	57.40	32.50	le90	1x	3.83		-	2	h2rbox-le90_r50_fpn_adamw-1x_dior

Original PyTorch Implementation (Paper)

Backbone	AP50:95	AP50	AP75	Angle	lr schd	Mem (GB)	Inf Time (fps)	MS	Batch Size	Configs
ResNet50 (1024,1024,200)	33.15	57.00	32.60	le90	1x	3.83		-	2	h2rbox_r50_adamw_fpn_1x_dior_le90

Notes

MS means multiple scale image split.
Inf Time was tested on a single RTX3090.
The memory log of MMRotate 1.x is dynamic, so the last iteration is recorded here.

codecov · 2022-11-25T03:58:44Z

Codecov Report

Base: 61.20% // Head: 80.35% // Increases project coverage by +19.15% 🎉

Coverage data is based on head (b06e250) compared to base (e8c6eb8).
Patch coverage: 90.25% of modified lines in pull request are covered.

❗ Current head b06e250 differs from pull request most recent head 7a73f36. Consider uploading reports for the commit 7a73f36 to get more accurate results

Additional details and impacted files

@@             Coverage Diff              @@
##           dev-1.x     #644       +/-   ##
============================================
+ Coverage    61.20%   80.35%   +19.15%     
============================================
  Files           96       98        +2     
  Lines         6562     6806      +244     
  Branches       932      960       +28     
============================================
+ Hits          4016     5469     +1453     
+ Misses        2329     1024     -1305     
- Partials       217      313       +96

Flag	Coverage Δ
unittests	`?`

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
mmrotate/models/detectors/h2rbox.py	`85.48% <85.48%> (ø)`
mmrotate/models/dense_heads/h2rbox_head.py	`89.83% <89.83%> (ø)`
mmrotate/datasets/__init__.py	`100.00% <100.00%> (ø)`
mmrotate/datasets/dota.py	`89.74% <100.00%> (+0.85%)`	⬆️
mmrotate/models/dense_heads/__init__.py	`100.00% <100.00%> (ø)`
mmrotate/models/detectors/__init__.py	`100.00% <100.00%> (ø)`
mmrotate/models/losses/__init__.py	`100.00% <100.00%> (ø)`
mmrotate/models/losses/h2rbox_consistency_loss.py	`100.00% <100.00%> (ø)`
mmrotate/evaluation/metrics/dota_metric.py	`87.00% <0.00%> (-1.13%)`	⬇️
... and 28 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.

docs/zh_cn/model_zoo.md

docs/en/model_zoo.md

mmrotate/models/dense_heads/h2rbox_head.py

mmrotate/models/losses/h2rbox_consistency_loss.py

zytx121

LGTM

liuyanyi

LGTM

* [Algorithm] Support H2RBox * upload config and readme * Update dota.py * update unit loss test * fix ci * delete useless codes * update other implementation * Create test_h2rbox_head.py * Upload 3x config * Update 3x performance * support dotav1.5 and dotav2 * Update h2rbox performance on dotav15 * Update dotav2 * Update dotav2.py * Update ms performance on dota * Update dotav2.py * Create h2rbox-le90_r50_fpn_adamw-1x_dotav2.py * Update performance on dotav2 * Create h2rbox-le90_r50_fpn_adamw-3x_dotav15.py * Update 3x performance on dotav15 * Create h2rbox-le90_r50_fpn_adamw-3x_dotav2.py * update 3x performance on dotav2 * Add H2Rbox in README * Add h2rbox in model zoo * Update test_dota.py * Create metafile.yml * Update weights and logs * Fix * Update __init__.py * Create h2rbox-le90_r50_fpn_adamw-1x_dior.py * Update performance on dior * Fix wrong param name Co-authored-by: Yue Zhou <592267829@qq.com>

[Algorithm] Support H2RBox

e0bc42a

yangxue0827 added WIP algorithm labels Nov 24, 2022

yangxue0827 added 4 commits November 25, 2022 00:04

upload config and readme

dcfccc8

Update dota.py

cb403aa

update unit loss test

de58670

fix ci

e6b33f5

yangxue0827 added 17 commits November 25, 2022 14:12

delete useless codes

7da3b8a

update other implementation

e123017

Create test_h2rbox_head.py

ff2500a

Upload 3x config

ffd3e2b

Update 3x performance

5f1109e

support dotav1.5 and dotav2

91e6914

Update h2rbox performance on dotav15

fdb6af0

Update dotav2

aa52be6

Update dotav2.py

80e8371

Update ms performance on dota

560ef4f

Update dotav2.py

45c45d5

Create h2rbox-le90_r50_fpn_adamw-1x_dotav2.py

b4f6ad3

Update performance on dotav2

ffb4bd0

Create h2rbox-le90_r50_fpn_adamw-3x_dotav15.py

817281e

Update 3x performance on dotav15

44cedab

Create h2rbox-le90_r50_fpn_adamw-3x_dotav2.py

62a146c

update 3x performance on dotav2

36294cf

yangxue0827 requested a review from zytx121 November 28, 2022 05:34

yangxue0827 added 4 commits November 28, 2022 14:39

Add H2Rbox in README

f5a6a06

Add h2rbox in model zoo

bc3f05f

Update test_dota.py

3a8bc6a

Create metafile.yml

7d008b2

Update weights and logs

0741121

yangxue0827 removed the WIP label Nov 29, 2022

zytx121 requested a review from liuyanyi November 29, 2022 08:10

zytx121 reviewed Nov 29, 2022

View reviewed changes

Fix

b06e250

zytx121 previously approved these changes Nov 30, 2022

View reviewed changes

Merge branch 'dev-1.x' into h2rbox

eed0a91

zytx121 dismissed their stale review via eed0a91 November 30, 2022 08:36

Update __init__.py

7a95922

zytx121 previously approved these changes Nov 30, 2022

View reviewed changes

liuyanyi previously approved these changes Dec 1, 2022

View reviewed changes

yangxue0827 added the WIP label Dec 1, 2022

yangxue0827 added 3 commits December 1, 2022 16:44

Create h2rbox-le90_r50_fpn_adamw-1x_dior.py

800716f

Update performance on dior

30adbf9

Fix wrong param name

7a73f36

yangxue0827 dismissed stale reviews from liuyanyi and zytx121 via 7a73f36 December 1, 2022 08:46

yangxue0827 removed the WIP label Dec 1, 2022

zytx121 approved these changes Dec 6, 2022

View reviewed changes

RangiLyu approved these changes Dec 6, 2022

View reviewed changes

RangiLyu merged commit 22320aa into open-mmlab:dev-1.x Dec 6, 2022

zytx121 mentioned this pull request Dec 30, 2022

Bump version to 1.0.0rc1 #676

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Algorithm] Support H2RBox #644

[Algorithm] Support H2RBox #644

yangxue0827 commented Nov 24, 2022 •

edited

Loading

codecov bot commented Nov 25, 2022 •

edited

Loading

zytx121 left a comment

liuyanyi left a comment

[Algorithm] Support H2RBox #644

[Algorithm] Support H2RBox #644

Conversation

yangxue0827 commented Nov 24, 2022 • edited Loading

Motivation

Modification

Performance

Notes

codecov bot commented Nov 25, 2022 • edited Loading

Codecov Report

zytx121 left a comment

Choose a reason for hiding this comment

liuyanyi left a comment

Choose a reason for hiding this comment

yangxue0827 commented Nov 24, 2022 •

edited

Loading

codecov bot commented Nov 25, 2022 •

edited

Loading