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.

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

Implementation of YOLACT forward_dummy to enable get_flops #6079

Merged
merged 12 commits into from
Oct 11, 2021

Conversation

collinzrj
Copy link
Contributor

Motivation

To enable the get_flops feature on YOLACT, the forward_dummy needs to be implemented

Modification

The forward_dummy function is implemented.

Closes #5891

@CLAassistant
Copy link

CLAassistant commented Sep 10, 2021

CLA assistant check
All committers have signed the CLA.

@codecov
Copy link

codecov bot commented Sep 10, 2021

Codecov Report

Merging #6079 (e0ac5b6) into master (db85fd1) will increase coverage by 0.38%.
The diff coverage is 100.00%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master    #6079      +/-   ##
==========================================
+ Coverage   61.44%   61.82%   +0.38%     
==========================================
  Files         304      315      +11     
  Lines       23855    25163    +1308     
  Branches     3942     4185     +243     
==========================================
+ Hits        14657    15558     +901     
- Misses       8415     8796     +381     
- Partials      783      809      +26     
Flag Coverage Δ
unittests 61.80% <100.00%> (+0.38%) ⬆️

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

Impacted Files Coverage Δ
mmdet/models/dense_heads/yolact_head.py 79.55% <100.00%> (+0.17%) ⬆️
mmdet/models/detectors/yolact.py 97.36% <100.00%> (+3.08%) ⬆️
mmdet/models/detectors/yolo.py 50.00% <0.00%> (-33.34%) ⬇️
mmdet/core/bbox/coder/yolo_bbox_coder.py 52.94% <0.00%> (-8.04%) ⬇️
mmdet/models/dense_heads/rpn_head.py 88.00% <0.00%> (-4.86%) ⬇️
mmdet/datasets/api_wrappers/coco_api.py 87.50% <0.00%> (-4.17%) ⬇️
mmdet/models/plugins/dropblock.py 91.89% <0.00%> (-2.40%) ⬇️
mmdet/models/utils/ckpt_convert.py 3.73% <0.00%> (-0.92%) ⬇️
mmdet/models/dense_heads/yolo_head.py 46.66% <0.00%> (-0.92%) ⬇️
mmdet/models/roi_heads/bbox_heads/bbox_head.py 78.87% <0.00%> (-0.75%) ⬇️
... and 35 more

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update db85fd1...e0ac5b6. Read the comment docs.

@collinzrj
Copy link
Contributor Author

@ZwwWayne

@collinzrj
Copy link
Contributor Author

The change does not influence test_yolo_normal, is there anything wrong with the CI?

@collinzrj
Copy link
Contributor Author

@RangiLyu

@collinzrj
Copy link
Contributor Author

My local lint passed, is there any updates on the docformatter check?

@RangiLyu
Copy link
Member

My local lint passed, is there any updates on the docformatter check?

My local lint passed too. Really wired. @hhaAndroid @ZwwWayne any ideas?

@collinzrj
Copy link
Contributor Author

collinzrj commented Oct 1, 2021

lint passed @RangiLyu

@collinzrj
Copy link
Contributor Author

The test failed for something not related to this change

Copy link
Member

@RangiLyu RangiLyu left a comment

Choose a reason for hiding this comment

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

LGTM

@ZwwWayne ZwwWayne merged commit 7f9facc into open-mmlab:master Oct 11, 2021
ZwwWayne pushed a commit to ZwwWayne/mmdetection that referenced this pull request Jul 19, 2022
…b#6079)

* update forward_dummy

* improve code

* fix lint

* include forward_dummy in unit test

* remove hardcode

* fix lint

* fix bug

* change simple_test to forward

* update forward_dummy

* fix problems

* add test comment

* fix lint
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Issue about tools\analysis_tools\get_flops.py
5 participants