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

[Enhancement] Delete convert function and add instruction to ViT/Swin README.md #791

Merged
merged 16 commits into from
Aug 25, 2021

Conversation

xiexinch
Copy link
Collaborator

Modification

  1. Delete convert function from ViT/Swin backbones.
  2. Add instructions to README.md

BC-breaking

Directly use other repositories' model links to start a train may not work, users must use convert scripts (#783 ) to preprocess pre-trained weights.

@codecov
Copy link

codecov bot commented Aug 14, 2021

Codecov Report

Merging #791 (9737d89) into master (f72727c) will increase coverage by 2.63%.
The diff coverage is 79.27%.

❗ Current head 9737d89 differs from pull request most recent head cbf309c. Consider uploading reports for the commit cbf309c to get more accurate results
Impacted file tree graph

@@            Coverage Diff             @@
##           master     #791      +/-   ##
==========================================
+ Coverage   86.09%   88.73%   +2.63%     
==========================================
  Files         108      107       -1     
  Lines        5862     5805      -57     
  Branches      953      932      -21     
==========================================
+ Hits         5047     5151     +104     
+ Misses        630      462     -168     
- Partials      185      192       +7     
Flag Coverage Δ
unittests 88.71% <79.27%> (+2.63%) ⬆️

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

Impacted Files Coverage Δ
mmseg/models/utils/__init__.py 100.00% <ø> (ø)
mmseg/apis/test.py 46.34% <48.27%> (+15.67%) ⬆️
mmseg/datasets/ade.py 90.90% <72.72%> (+50.36%) ⬆️
mmseg/datasets/cityscapes.py 85.00% <75.00%> (+63.65%) ⬆️
mmseg/datasets/custom.py 92.13% <93.33%> (+2.31%) ⬆️
mmseg/core/evaluation/__init__.py 100.00% <100.00%> (ø)
mmseg/core/evaluation/eval_hooks.py 72.54% <100.00%> (+4.36%) ⬆️
mmseg/core/evaluation/metrics.py 90.62% <100.00%> (+1.33%) ⬆️
mmseg/models/backbones/swin.py 87.41% <100.00%> (+0.51%) ⬆️
mmseg/models/backbones/vit.py 86.79% <100.00%> (+1.94%) ⬆️
... and 3 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 f72727c...cbf309c. Read the comment docs.

Copy link
Collaborator

@xvjiarui xvjiarui left a comment

Choose a reason for hiding this comment

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

LGTM.
Please resolve the conflict.

configs/swin/README.md Outdated Show resolved Hide resolved
configs/vit/README.md Outdated Show resolved Hide resolved
@xvjiarui
Copy link
Collaborator

The url in config files should be removed.

@Junjun2016
Copy link
Collaborator

Unitests are failed.

@xvjiarui xvjiarui merged commit c11da07 into open-mmlab:master Aug 25, 2021
bowenroom pushed a commit to bowenroom/mmsegmentation that referenced this pull request Feb 25, 2022
… README.md (open-mmlab#791)

* delete convert function and add instruction to README.md

* unified model convert and README

* remove url

* fix import error

* fix unittest

* rename pretrain

* rename vit and deit pretrain

* Update upernet_deit-b16_512x512_160k_ade20k.py

* Update upernet_deit-b16_512x512_80k_ade20k.py

* Update upernet_deit-b16_ln_mln_512x512_160k_ade20k.py

* Update upernet_deit-b16_mln_512x512_160k_ade20k.py

* Update upernet_deit-s16_512x512_160k_ade20k.py

* Update upernet_deit-s16_512x512_80k_ade20k.py

* Update upernet_deit-s16_ln_mln_512x512_160k_ade20k.py

* Update upernet_deit-s16_mln_512x512_160k_ade20k.py

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
sibozhang pushed a commit to sibozhang/mmsegmentation that referenced this pull request Mar 22, 2024
* supoort pytorch 1.8 CI

* mmcv latest

* torchvision issue

* fix

* fix

* pt1.3

* pt1.3
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.

3 participants