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

compare #2

Closed
wants to merge 381 commits into from
Closed

compare #2

wants to merge 381 commits into from

Conversation

bowenroom
Copy link
Owner

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Modification

Please briefly describe what modification is made in this PR.

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

  1. Pre-commit or other linting tools are used to fix the potential lint issues.
  2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
  3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMDet3D.
  4. The documentation has been modified accordingly, like docstring or example tutorials.

xvjiarui and others added 30 commits April 27, 2021 23:51
@xvjiarui
[Refactor] Use MMCV MODEL_REGISTRY (open-mmlab#515)
d568d06 
* [Refactor] Use MMCV MODEL_REGISTRY

* fixed args
@grimoire
[Feature] add onnxruntime test tool (open-mmlab#498)
bdf5adf 
* add onnxruntime test tool, update pytorch2onnx to support slice export

* onnx convert with custom output shape, update test code

* update pytorch2onnx, add rescale_shape support, add document

* update doc for lint error fixing

* remove cpu flag in ort_test.py

* change class name, fix cuda error

* remote comment

* fix bug of torch2onnx

* mIOU to mIoU
@Wuziyi616
[Enhance] Replace data_dict calling 'img' key to support MMDet3D (ope…
768f704 
…n-mmlab#514)

* remove dict calling img key for compatibility

* fix unit test

* infer batch size using len(result) to be consistent with mmcv
@Wuziyi616
[Enhance] Support reading class_weight from file in loss functions to…
cef8a4f 
… help MMDet3D (open-mmlab#513)

* support reading class_weight from file in loss function

* add unit test of loss with class_weight from file

* minor fix

* move get_class_weight to utils
@clownrat6 @xvjiarui
Adjust vision transformer backbone architectures (open-mmlab#524)
cf2cb54 
* Adjust vision transformer backbone architectures;

* Add DropPath, trunc_normal_ for VisionTransformer implementation;

* Add class token buring intermediate period and remove it during final period;

* Fix some parameters loss bug;

* * Store intermediate token features and impose no processes on them;

* Remove class token and reshape entire token feature from NLC to NCHW;

* Fix some doc error

* Add a arg for VisionTransformer backbone to control if input class token into transformer;

* Add stochastic depth decay rule for DropPath;

* * Fix output bug when input_cls_token=False;

* Add related unit test;

* * Add arg: out_indices to control model output;

* Add unit test for DropPath;

* Apply suggestions from code review

Co-authored-by: Jerry Jiarui XU <[email protected]>
@sshuair
add metric mFscore (open-mmlab#509)
e16e0e3 
* add mFscore and refactor the metrics return value

* fix linting

* some docstring and name fix
@xvjiarui
Use MMCV's EvalHook in MMSegmentation (open-mmlab#438)
f933603 
* mmcv eval hook

* mmcv evalhook compatible

* add warnings

* inherit from base class

* fix unitest

* adapt to mmcv 1.3.1

* fixed unittest

* set by_epoch=False

* fixed efficient test

* update docstring

Co-authored-by: Jiarui XU <[email protected]>
@xvjiarui
Bump to v0.13 (open-mmlab#529)
f884489
@clownrat6
Add option for output shape of ViT (open-mmlab#530)
aa9b609 
* Add arg: final_reshape to control if converting output feature information from NLC to NCHW;

* Fix the default value of final_reshape;

* Modify arg: final_reshape to arg: out_shape;

* Fix some unit test bug;
@RangiLyu
fix typo (open-mmlab#533)
4403923
@Wuziyi616
infer batch size using len(result) in test function (open-mmlab#532)
db44d16
support loading deit weights (open-mmlab#538)
584f5a7
add onnx to tensorrt tools (open-mmlab#542)
805eda8
fix verify bugs (open-mmlab#547)
8558163 
* fix verify bugs

* rename args
@clownrat6
[Feature] Add results2img, format_results for ade dataset (open-mmlab…
524425c 
…#544)

* [Feature] Add results2img, format_results for ade dataset.

* clean rebundant code.
@clownrat6
Add compatible MMSegmentation and MMCV version table. (open-mmlab#558)
63a9516
@edwardyehuang
DeepLab V3 did not present in CVPR 2017 (open-mmlab#560)
66b0525 
https://openaccess.thecvf.com/CVPR2017 does not contain DeepLabV3
[Feature] Update deploy test tools (open-mmlab#553)
dc5d53b 
* add trt test tool

* create deploy_test, update document

* fix with isort

* move import inside __init__

* remove comment, fix doc

* update document
[Feature] support mim (open-mmlab#549)
a95f6d8 
* dice loss

* format code, add docstring and calculate denominator without valid_mask

* minor change

* restore

* add metafile

* add manifest.in and add config at setup.py

* add requirements

* modify manifest

* modify manifest

* Update MANIFEST.in

* add metafile

* add metadata

* fix typo

* Update metafile.yml

* Update metafile.yml

* minor change

* Update metafile.yml

* add subfix

* fix mmshow

* add more  metafile

* add config to model_zoo

* fix bug

* Update mminstall.txt

* [fix] Add models

* [Fix] Add collections

* [fix] Modify collection name

* [Fix] Set datasets to unet metafile

* [Fix] Modify collection names

* complement inference time
@yinchimaoliang @xvjiarui
[feature]: Able to use save_best option (open-mmlab#575)
9dd3e15 
* Add  save_best option in eval_hook.

* Update meta to fix best model can not test bug

* refactor with _do_evaluate

* remove redundent

* add meta

Co-authored-by: Jiarui XU <[email protected]>
@xvjiarui
Bump to v0.14 (open-mmlab#580)
5d46314
@xvjiarui
[Refactor]: Unified parameter initialization (open-mmlab#567)
0c5b026 
* [Refactor]: Unified parameter initialization

* fixed pretrained
@xvjiarui
Bump to v0.14.1 (open-mmlab#604)
2603216
@clownrat6
[Feature] Move 'Install MMCV' to a independent CI item. (open-mmlab#602)
608f842 
* [Feature] Move 'Install MMCV' to a independent CI item.

* Merge MMCV install into MMSEG dependencies install

* Fix bug of 'Install MMCV'

* Remove duplicate CI items

* Fix torch device

* Split cpu env and gpu env into two CI project

* Fix some mmdet related bugs

* Fix mmcv-full install bug of build_cpu CI project.
@clownrat6
[Refactor] Using mmcv transformer bricks to refactor vit. (open-mmlab…
8f8abe3 
…#571)

* [Refactor] Using mmcv bricks to refactor vit

* Follow the vit code structure from mmclassification

* Add MMCV install into CI system.

* Add  to 'Install MMCV' CI item

* Add 'Install MMCV_CPU' and 'Install MMCV_GPU CI' items

* Fix & Add

1. Fix low code coverage of vit.py;

2. Remove HybirdEmbed;

3. Fix doc string of VisionTransformer;

* Add helpers unit test.

* Add converter to convert vit pretrain weights from timm style to mmcls style.

* Clean some rebundant code and refactor init

1. Use timm style init_weights;

2. Remove to_xtuple and trunc_norm_;

* Add comments for VisionTransformer.init_weights()

* Add arg: pretrain_style to choose timm or mmcls vit pretrain weights.
@Junjun2016
fix typo and link (open-mmlab#608)
0076913 
Co-authored-by: hejunjun <[email protected]>
@amrit110
Add fixes to Dockerfile (open-mmlab#607)
458fc78
@clownrat6
[Fix] Fix some vit init bugs (open-mmlab#609)
0c4c3b7 
* [Fix] Fix vit init bug

* Add some vit unit tests

* Modify module import

* Fix pretrain weights bug

* Modify pretrained judge

* Add some unit tests to improve code cov

* Optimize code

* Fix vit unit test
@Junjun2016
change inference time from fps to ms/im
3856453
@Junjun2016
add_pr_template
e71766c
xvjiarui and others added 26 commits February 9, 2022 00:52
@xvjiarui
[Improve] Use MMCV load_state_dict func in ViT/Swin (open-mmlab#1272)
66b778c 
* [Improve] Use MMCV load_state_dict func in ViT/Swin

* use CheckpointLoader instead
@xvjiarui
[Improve] Add exception for PointRend for support CPU-only usage (ope…
82a8088 
…n-mmlab#1271)

* [Improve] Add exception for PointRend for support CPU-only usage

* fixed linting
@MengzhangLI
Bump v0.21.1 (open-mmlab#1273)
a39f585 
* Bump v0.21.1

* add improvements in changelog

* add improvements in changelog

* fix cn readme

* change changelog
@MengzhangLI
[Fix] Fix type in Swin Transformer (open-mmlab#1274)
b163101
@CuriseJia
fix-demo (open-mmlab#1269)
9c56c2d
@andife
Update MMSegmentation_Tutorial.ipynb (open-mmlab#1281)
68cfdc7
@SBCV
Fix bug in conversion of potsdam (open-mmlab#1279)
0934a57
@HJoonKwon
[Fix] Make accuracy take into account ignore_index (open-mmlab#1259)
346f70d 
* make accuracy take into account ignore_index

* add UT for accuracy
@MengzhangLI
[Enhancement] Update the installation of MMCV (open-mmlab#1275)
d9eb6d0 
* Update the installation of MMCV

* use matrix.torch_version

* fix typo in doc

* fix docs

* fix colab

* change docs
@Tsingularity
Update get_started.md (open-mmlab#1290)
92068b4 
fix wrong file format. it should be png instead of jpg
@MengzhangLI
[Fix] Add Pytorch HardSwish assertion in unit test (open-mmlab#1294)
0e3d1b8 
* assert original HardSwish when PyTorch > 1.6 in unit test

* assert original HardSwish when PyTorch > 1.6 in unit test

* assert original HardSwish when PyTorch > 1.6 in unit test

* assert original HardSwish when PyTorch > 1.6 in unit test

* assert original HardSwish when PyTorch > 1.6 in unit test

* assert original HardSwish when PyTorch > 1.6 in unit test
@MengzhangLI
[Fix] Fix wrong palette value in vaihingen (open-mmlab#1292)
2056caa
@RockeyCoss
[Fix] Fix the bug that setr cannot load pretrain (open-mmlab#1293)
9522b4f 
* [Fix] Fix the bug that setr cannot load pretrain

* delete new pretrain
@Waterman0524 @MengzhangLI
[Feature] Support iSAID aerial dataset. (open-mmlab#1115)
4f4e772 
* support iSAID aerial dataset

* Update and rename docs/dataset_prepare.md to 博士/dataset_prepare.md

* Update dataset_prepare.md

* fix typo

* fix typo

* fix typo

* remove imgviz

* fix wrong order in annotation name

* upload models&logs

* upload models&logs

* add load_annotations

* fix unittest coverage

* fix unittest coverage

* fix correct crop size in config

* fix iSAID unit test

* fix iSAID unit test

* fix typos

* fix wrong crop size in readme

* use smaller figure as test data

* add smaller dataset in test data

* add blank in docs

* use 0 bytes pseudo data

* add footnote and comments for crop size

* change iSAID to isaid and add default value in it

* change iSAID to isaid in _base_

Co-authored-by: MengzhangLI <[email protected]>
@MengzhangLI
[Fix] Fix iSAID dataset conversion default setting in doc. (open-mmla…
71c201b 
…b#1298)
@bowenroom
Merge pull request #1 from open-mmlab/master
1a5a033 
Merge
@bowenroom
channel order changed
cecb9d5
@MengzhangLI
[Doc] add MMRotate link (open-mmlab#1308)
72ff12f
@bowenroom
add ignore
77aac39
@bowenroom
Merge branch 'open-mmlab:master' into master
559b16b
@bowenroom
Merge branches 'master' and 'master' of https://github.91chi.fun//htt…
e20507e 
…ps://github.com/bowenroom/mmsegmentation
@MengzhangLI
[Enhancement] Add win-ci (open-mmlab#1296)
6ff724e 
* [Enhancement] Add win-ci

* add timm in win unittest

* remove mmflow with mmseg in win unittest

* remove opencv-python in requirements

* add opencv2 back

* move opencv installation into build.yml
@bowenroom
Merge branch 'open-mmlab:master' into master
5756f9e
@MengzhangLI
[Fix] Update correct In Collection in metafile of each configs. (op…
8cf333c 
…en-mmlab#1239)

* change md2yml file

* update metafile

* update twins In Collection automatically

* fix twins metafile

* fix twins metafile

* all metafile use value of Method

* update collect name

* update collect name

* fix some typo

* fix FCN D6

* change JPU to FastFCN

* fix some typos in DNLNet, NonLocalNet, SETR, Segmenter, STDC, FastSCNN

* fix typo in stdc

* fix typo in DNLNet and UNet

* fix NonLocalNet typo
@MeowZheng
[Enhancement] Revise pre-commit-hooks (open-mmlab#1315)
e5cd755
@bowenroom
Merge branch 'open-mmlab:master' into master
b3e20be
bowenroom pushed a commit that referenced this pull request Feb 25, 2022
@lkm2835 @Younghoon-Lee @MeowZheng
[Feature] Add MultiImageMixDataset (open-mmlab#1105)
88944e9 
* Fix typo in usage example

* original MultiImageMixDataset code in mmdet

* Add MultiImageMixDataset unittests in test_dataset_wrapper

* fix lint error

* fix value name ann_file to ann_dir

* modify retrieve_data_cfg (#1)

* remove dynamic_scale & add palette

* modify retrieve_data_cfg method

* modify retrieve_data_cfg func

* fix error

* improve the unittests coverage

* fix unittests error

* Dataset (#2)

* add cfg-options

* Add unittest in test_build_dataset

* add blank line

* add blank line

* add a blank line

Co-authored-by: Miao Zheng <[email protected]>

Co-authored-by: Younghoon-Lee <[email protected]>
Co-authored-by: MeowZheng <[email protected]>
Co-authored-by: Miao Zheng <[email protected]>
bowenroom pushed a commit that referenced this pull request Feb 25, 2022
@lkm2835 @Younghoon-Lee @MeowZheng
[Fix] Improve MultiImageMixDataset unittests coverage (open-mmlab#1197)
4c72157 
* Fix typo in usage example

* original MultiImageMixDataset code in mmdet

* Add MultiImageMixDataset unittests in test_dataset_wrapper

* fix lint error

* fix value name ann_file to ann_dir

* modify retrieve_data_cfg (#1)

* remove dynamic_scale & add palette

* modify retrieve_data_cfg method

* modify retrieve_data_cfg func

* fix error

* improve the unittests coverage

* fix unittests error

* Dataset (#2)

* add cfg-options

* Add unittest in test_build_dataset

* add blank line

* add blank line

* add a blank line

Co-authored-by: Miao Zheng <[email protected]>

* [Fix] Add MultiImageMixDataset unittests

Co-authored-by: Younghoon-Lee <[email protected]>
Co-authored-by: MeowZheng <[email protected]>
Co-authored-by: Miao Zheng <[email protected]>
@bowenroom bowenroom closed this Feb 25, 2022
@bowenroom
Copy link
Owner Author

000

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.