Skip to content

[Feature] Add Mosaic transform#1093

Merged
Junjun2016 merged 21 commits intoopen-mmlab:masterfrom
lkm2835:mosaic
Jan 11, 2022
Merged

[Feature] Add Mosaic transform#1093
Junjun2016 merged 21 commits intoopen-mmlab:masterfrom
lkm2835:mosaic

Conversation

@lkm2835
Copy link
Copy Markdown
Contributor

@lkm2835 lkm2835 commented Nov 30, 2021

Modification

mmseg/datasets/pipelines/transforms.py: Add class Mosaic
tests/test_data/test_transform.py: Add test_mosaic
mmseg/datasets/pipelines/__init__.py: import Mosaic

original code: Mosaic, test_mosaic in mmdet

@Junjun2016
Copy link
Copy Markdown
Collaborator

Junjun2016 commented Nov 30, 2021

Hi @lkm2835
Thanks for your contribution again.
@RockeyCoss please review it and do some ablation studies.

@Junjun2016 Junjun2016 self-requested a review November 30, 2021 16:38
Junjun2016
Junjun2016 reviewed Nov 30, 2021
View reviewed changes
Junjun2016
Junjun2016 reviewed Nov 30, 2021
View reviewed changes
Copy link
Copy Markdown
Collaborator

@Junjun2016 Junjun2016 left a comment

Choose a reason for hiding this comment

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

We may also need MultiImageMixDataset.

@Junjun2016
Copy link
Copy Markdown
Collaborator

Junjun2016 commented Nov 30, 2021

We may also need MultiImageMixDataset.

Can adjust MultiImageMixDataset in mmdet (https://github.com/open-mmlab/mmdetection/blob/f08548bfd6d394a82566022709b5ce9e6b0a855e/mmdet/datasets/dataset_wrappers.py#L289) to mmseg accordingly.

@lkm2835
Copy link
Copy Markdown
Contributor Author

lkm2835 commented Nov 30, 2021

We may also need MultiImageMixDataset.

I'll prepare and create another PR.

@Junjun2016
Copy link
Copy Markdown
Collaborator

Junjun2016 commented Nov 30, 2021

We may also need MultiImageMixDataset.

I'll prepare and create another PR.

Great, it is better to add some results on your own datasets or mmseg supported datasets.

@codecov
Copy link
Copy Markdown

codecov bot commented Dec 1, 2021 •
edited
Loading

Codecov Report

Attention: Patch coverage is 97.72727% with 2 lines in your changes missing coverage. Please review.

Project coverage is 90.17%. Comparing base (7f06e01) to head (5bd9cb8).
Report is 254 commits behind head on master.

Files Patch % Lines
mmseg/datasets/pipelines/transforms.py 97.72% 2 Missing ⚠️
Additional details and impacted files 
@@            Coverage Diff             @@
##           master    #1093      +/-   ##
==========================================
+ Coverage   90.07%   90.17%   +0.09%     
==========================================
  Files         125      125              
  Lines        7268     7356      +88     
  Branches     1206     1218      +12     
==========================================
+ Hits         6547     6633      +86     
- Misses        518      520       +2     
  Partials      203      203
Flag Coverage Δ
unittests 90.17% <97.72%> (+0.09%) ⬆️

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

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@Junjun2016 Junjun2016 requested a review from RockeyCoss December 1, 2021 12:09
@lkm2835 lkm2835 mentioned this pull request Dec 6, 2021
Merged
Junjun2016
Junjun2016 reviewed Dec 6, 2021
View reviewed changes
Junjun2016
Junjun2016 reviewed Dec 6, 2021
View reviewed changes
Junjun2016
Junjun2016 reviewed Dec 6, 2021
View reviewed changes
RockeyCoss
RockeyCoss suggested changes Dec 9, 2021
View reviewed changes
@RockeyCoss
Copy link
Copy Markdown
Contributor

RockeyCoss commented Dec 15, 2021

@lkm2835 Hi，The results are as follows:

exp_num method mIoU best best index mIoU last last index
1 deeplabv3_r50-d8_512x512_160k_ade20k 0.43 10 0.43 10
2 deeplabv3_r50-d8_512x512_160k_ade20k_mosaic_0.2-1.8 0.4316 10 0.4316 10
3 deeplabv3_r50-d8_512x512_160k_ade20k_mosaic_0.5-1.5 0.4326 10 0.4326 10
4 deeplabv3_r50-d8_512x512_160k_ade20k_mosaic_0.8-1.2 0.4283 10 0.4283 10

We can see that

@lkm2835
Copy link
Copy Markdown
Contributor Author

lkm2835 commented Dec 16, 2021

We have done different img scales test for Mosaic augmentation.

The results are as follows:
[Feature] Add MultiImageMixDataset #1105

MeowZheng
MeowZheng reviewed Jan 7, 2022
View reviewed changes
MeowZheng
MeowZheng reviewed Jan 7, 2022
View reviewed changes
MeowZheng
MeowZheng reviewed Jan 7, 2022
View reviewed changes
MeowZheng
MeowZheng reviewed Jan 7, 2022
View reviewed changes
MeowZheng
MeowZheng reviewed Jan 7, 2022
View reviewed changes
@CLAassistant
Copy link
Copy Markdown

CLAassistant commented Jan 7, 2022 •
edited
Loading

CLA assistant check
All committers have signed the CLA.

@RockeyCoss RockeyCoss mentioned this pull request Jan 11, 2022
Merged
@Junjun2016 Junjun2016 merged commit f0262fa into open-mmlab:master Jan 11, 2022
bowenroom pushed a commit to bowenroom/mmsegmentation that referenced this pull request Feb 25, 2022
@lkm2835 @MeowZheng
[Feature] Add Mosaic transform (open-mmlab#1093)
e9dd32b 
* Fix typo in usage example

* original mosaic code in mmdet

* Adjust mosaic to the semantic segmentation

* Remove bbox test in test_mosaic

* Add unittests

* Fix resize mode for seg_fields

* Fix repr error

* modify Mosaic docs

* modify from Mosaic to RandomMosaic

* Add docstring

* modify Mosaic docstring

* [Docs] Add a blank line before Returns:

* add blank lines

Co-authored-by: MeowZheng <meowzheng@outlook.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@Junjun2016 Junjun2016 Junjun2016 left review comments

@MeowZheng MeowZheng MeowZheng approved these changes

+1 more reviewer

@RockeyCoss RockeyCoss RockeyCoss approved these changes

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@lkm2835 @Junjun2016 @RockeyCoss @CLAassistant @MeowZheng