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.

Sign up for GitHub

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

Jump to bottom

[Feature] add DPT head #605

Merged
merged 48 commits into from Aug 30, 2021
Merged

[Feature] add DPT head #605

merged 48 commits into from Aug 30, 2021

Conversation

xiexinch
Copy link
Collaborator

@xiexinch xiexinch commented Jun 17, 2021 •
edited

Implementation of Vision Transformers for Dense Prediction.
Modified from the official repository.

Training results:

backbone mIoU mIoU (ms+flip)
ViT-B 46.97 48.34
ViT-L 46.19 46.97

Different from the original paper, I train with AdamW optimizer instead of SGD.

@codecov
Copy link

codecov bot commented Jun 17, 2021 •
edited

Codecov Report

Merging #605 (522cdff) into master (5753f41) will increase coverage by 0.13%.
The diff coverage is 96.19%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #605      +/-   ##
==========================================
+ Coverage   88.76%   88.90%   +0.13%     
==========================================
  Files         109      110       +1     
  Lines        5823     5928     +105     
  Branches      935      950      +15     
==========================================
+ Hits         5169     5270     +101     
- Misses        463      465       +2     
- Partials      191      193       +2
Flag Coverage Δ
unittests 88.88% <96.19%> (+0.13%) ⬆️

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

Impacted Files Coverage Δ
mmseg/models/decode_heads/dpt_head.py 96.15% <96.15%> (ø)
mmseg/models/decode_heads/__init__.py 100.00% <100.00%> (ø)

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 5753f41...522cdff. Read the comment docs.

Junjun2016
Junjun2016 reviewed Aug 25, 2021
View reviewed changes
configs/dpt/README.md Outdated Show resolved Hide resolved
Junjun2016
Junjun2016 reviewed Aug 25, 2021
View reviewed changes
Copy link
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.

Add this method to Supported methods (Chinese and English) https://github.com/open-mmlab/mmsegmentation#benchmark-and-model-zoo.

Junjun2016
Junjun2016 reviewed Aug 25, 2021
View reviewed changes
README.md Outdated Show resolved Hide resolved
Junjun2016
Junjun2016 requested changes Aug 27, 2021
View reviewed changes
Copy link
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.

Please fix the conflict.

@xvjiarui
Copy link
Collaborator

LGTM except for one comment.

Please resolve the conflict btw.

@Junjun2016
Copy link
Collaborator

Check checkpoints' keys, maybe you should update keys.

@Junjun2016 Junjun2016 merged commit 2825efe into open-mmlab:master Aug 30, 2021
bowenroom pushed a commit to bowenroom/mmsegmentation that referenced this pull request Feb 25, 2022
@Junjun2016
[Feature] add DPT head (open-mmlab#605)
ef4b300 
* add DPT head

* [fix] fix init error

* use mmcv function

* delete code

* remove transpose clas

* support NLC output shape

* Delete post_process_layer.py

* add unittest and docstring

* rename variables

* fix project error and add unittest

* match dpt weights

* add configs

* fix vit pos_embed bug and dpt feature fusion bug

* match vit output

* fix gelu

* minor change

* update unitest

* fix configs error

* inference test

* remove auxilary

* use local pretrain

* update training results

* update yml

* update fps and memory test

* update doc

* update readme

* add yml

* update doc

* remove with_cp

* update config

* update docstring

* remove dpt-l

* add init_cfg and modify readme.md

* Update dpt_vit-b16.py

* zh-n README

* use constructor instead of build function

* prevent tensor being modified by ConvModule

* fix unittest

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
aravind-h-v pushed a commit to aravind-h-v/mmsegmentation that referenced this pull request Mar 27, 2023
@mishig25
Mv weights name consts to diffusers.utils (open-mmlab#605)
8685699
wjkim81 pushed a commit to wjkim81/mmsegmentation that referenced this pull request Dec 3, 2023
@jin-s13
update animal pose (open-mmlab#605)
84289b6
sibozhang pushed a commit to sibozhang/mmsegmentation that referenced this pull request Mar 22, 2024
Update big models (open-mmlab#605)
b7b40a1 
* Add configs and some stats.

* Update.

* Update r101 8x8.

* Minor.

* Update url.

* Update changelog.

* Fix typos and workdir.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@xvjiarui xvjiarui xvjiarui left review comments

@Junjun2016 Junjun2016 Junjun2016 approved these changes

@sennnnn sennnnn Awaiting requested review from sennnnn

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
3 participants
@xiexinch @xvjiarui @Junjun2016