Commit Graph

331 Commits (ae516155411239454901187bc71d225dcda3ad08)
 

Author SHA1 Message Date
MengzhangLI ae51615541 fix changelog link (#1190) 2022-01-10 09:05:09 -08:00
MengzhangLI 13d52c880b [Doc] Add MMDeploy link. #1174 2021-12-30 17:27:59 +08:00
MengzhangLI 2b4076add8 [Fix] Add note in UNet readme.md #1163 2021-12-24 23:29:59 +08:00
MengzhangLI 202eb2fde4 [Doc] Add MMSelfSup and MMRazor links #1162 2021-12-24 18:00:17 +08:00
MengzhangLI f3cd764f55 [Feature] Add UNet benchmark with multiple losses supervision (#1143)
* upload models and new configs

* fix hrf readme error

* fix hrf readme error

* add mDice of old models

* refactor configs
2021-12-23 21:38:51 +08:00
Rockey 6a7db50ac0 [Feature] Add segformer‘s benchmark on cityscapes (#1155)
* add segformer cityscapes' benchmark

* Update configs/segformer/README.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-12-23 15:42:42 +08:00
jbwang1997 44d4c3877e [Fix] Set random seed for generating `palette` if not given. (#1152)
* Fix colors

* fix comments

* Add comments

* Add comments. Add random seed in datasets
2021-12-23 09:51:50 +08:00
Junjun2016 e0b4f556d4 [Fix] Fix the model statistics in doc for readthedoc #1153 2021-12-20 23:52:53 +08:00
MengzhangLI 4a90241f91 [Docs] Refactor the structure of documentation (#1128)
* merge docs/ and docs_zh-CN/

* merge docs/ and docs_zh-CN/

* merge docs/ and docs_zh-CN/

* merge docs/ and docs_zh-CN/

* fix launch utility url

* fix launch utility url

* fix wrong pytorch doc url

* remove wrong links docs//
2021-12-16 18:56:45 +08:00
MengzhangLI fbcfa0568b Bump v0.20.2 #1141 2021-12-15 16:49:42 +08:00
Rockey a7595c6ec6 [Fix] revise --option to --options #1140 2021-12-15 15:24:08 +08:00
MengzhangLI a87de3c025 Bump to v0.20.1 (#1138)
* bump version 0.20.1

* bump version 0.20.1
2021-12-14 22:32:11 +08:00
MengzhangLI f0d47000fc [Fix] Fix correct num_classes of HRNet in LoveDA dataset #1136 2021-12-14 19:49:24 +08:00
MengzhangLI e2ff55d28a [Fix] Add <!-- [ABSTRACT] --> in metafile #1127 2021-12-14 19:12:56 +08:00
Rockey 3a1f4285b9 [Feature] Change options to cfg-option (#1129)
* [Feature] Change option to cfg-option

* add expire date and fix the docs

* modify docstring
2021-12-14 19:11:52 +08:00
MengzhangLI 520372eec8 Bump v0.20.0 (#1124)
* change version to v0.20.0

* change version to v0.20.0

* change version to v0.20.0
2021-12-11 01:43:29 +08:00
MengzhangLI c1e72513c9 [Feature] Support STDC Network (new) (#995)
* refactor stdc code

* update key

* fix backbone inference

* remove comments

* fixing errors

* fixing version conflict

* fux typo

* use STDCHead

* upload models&logs

* adding model converters script and fix unittest

* fix error

* fix error

* fix error

* delete redundant keys in config

* fix errors in configs and unittest

* fix errors in configs and unittest

* fix errors in configs and unittest

* change Memory name

* refactor stdc2mmseg

* change name to STDC

* refactor stdc

* refactor stdc

* stdc refactor

* stdc refactor

* stdc refactor

* stdc refactor

* stdc refactor

* stdc refactor

* refactor stdc

* stdc refactor

Co-authored-by: xiexinch <xinchen.xie@qq.com>
2021-12-10 23:09:32 +08:00
MengzhangLI 02b36fad28 [Fix] Unified links of readthedocs in docs (#1119)
* change readthedocs

* change readthedocs

* change readthedocs
2021-12-10 16:49:45 +08:00
Lxinyang cd246e3635 [Feature] Support Twins (NeurIPS2021) (#989)
* debug

* debug

* debug

* this is a debug step, and needs to be recovered

* need recover

* git

* debug

* git

* git

* git

* git

* git

* git

* debug need recover

* debug

* git

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debugf

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* git

* git

* git

* use config small/base/large

* debug

* debug

* git

* debug

* git

* debug

* debug

* debug args

* debug

* debug

* git

* git

* debug

* git

* git

* git

* git

* git

* debug

* debug

* git

* debug

* git

* debug

* debug

* debug

* debug

* git

* debug

* git

* git

* debug

* debug

* git

* git

* git

* git

* debug

* debug

* debug

* debug

* git

* debug

* debug

* git

* git

* debug

* debug

* git

* debug

* debug

* debug

* git

* debug

* debug

* debug

* Please enter the commit message for your changes. Lines starting

* git

* git

* debug

* debug

* debug

* git

* git

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* git

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* git

* fix pre-commit error

* fix error

* git

* git

* git

* git

* git

* git

* debug

* debug

* debug

* debug

* debug

* debug

* git

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* git

* git

* git

* debug

* debug

* debug

* git

* git

* git

* git

* git

* git

* git

* git

* git

* debug

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* fix unittest error

* fix config errors

* fix twins2mmseg bug

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* fix init_weights() in twins.py

* git

* git

* git

* git

* fix comment

* fix comment

* fix comment

* fix comment

* fix unit test coverage in TwinsPR

* Add Twins README

* Add Twins README

* twins refactor

* twins refactor

* delete init_cfg in FFN

* delete init_cfg in FFN

* Update mmseg/models/backbones/twins.py

* Update mmseg/models/backbones/twins.py

* Update mmseg/models/backbones/twins.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* Update mmseg/models/backbones/twins.py

* add conference name

Co-authored-by: linxinyang <linxinyang@meituan.com>
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-12-09 19:18:10 +08:00
MengzhangLI 12d902c02c [Fix] Cancel previous runs that are not completed #1118 2021-12-09 15:56:22 +08:00
MengzhangLI 2e4da3ea75 [Fix] Fix typo `ADE20k` to `ADE20K` in metafile #1120 2021-12-09 15:37:07 +08:00
Junjun2016 24b4761d83 [Fix] Fix symlink failure on Windows (#1038)
* fix symlink failure on Windows

* fix develop mode on windows
2021-12-08 23:19:23 -08:00
Rockey a370777e3b [Fix] Fix the bug that mit cannot process init_cfg (#1102)
* [Fix] Fix the bug that mit cannot process init_cfg

* fix error
2021-12-08 23:17:43 -08:00
irvingzhang0512 0d3ee4b520 [Feature] Support video demo (#1014)
* First commit for video demo

* fix lint

* update

* fix

* add wget in shell
2021-12-08 23:14:30 -08:00
Rockey 0ad0303ebc [Fix] Remove the inplace operation in uper_head and fpn_neck (#1103)
* [Fix] Remove the inplace operation in  uper_head

* remove the inplace operation in fpn neck

* fix conflict

* increase the coverage
2021-12-09 12:12:31 +08:00
Han Zhang e06cbcd8b1 [Fix] Fix dist training infinite waiting issue (#1035)
* [#1034] fix dist training infinite waiting issue

* print log_vars keys in assertion msg

* linting issue
2021-12-08 21:02:41 +08:00
MengzhangLI 593dcd3e7f [Fix] Fix MMHuman3D description and BiSeNetV2 FP16 hyperlink (#1111)
* fix mmhuman3d readme

* fix mmhuman3d readme
2021-12-07 15:51:18 +08:00
Zhaolun Zou 079c520e58 [Fix] Fix test error when using --show-dir (#1091)
* Fix test error when using --show-dir

* Move show before test

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
2021-12-06 08:10:18 -08:00
KangBK0120 3d58196e62 [Fix] Remove unexist arg in docstring #1106 2021-12-06 20:03:25 +08:00
Junjun2016 b8ca9b6d99 [Fix] Fix wrong init usage in transformer models (#1069)
* fix wrong trunc_normal_init usage

* fix mit init weights

* fix vit init weights

* fix mit init weights

* fix typo

* fix swin init weights
2021-12-06 19:59:33 +08:00
Rockey 6a3c31ae3f [Feature] add setr cityscapes benchmark (#1087)
* [Feature] add setr cityscapes benchmark

* change pretrain

* Update configs/_base_/datasets/cityscapes_768x768.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* remove redundant keys

* remove redundant keys

* fix lint error

* update readme

* update pretrain

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-12-03 00:18:50 -08:00
Rockey 07cd6c98e0 [Feature] Add focal loss (#1024)
* [Feature] add focal loss

* fix the bug of 'non' reduction type

* refine the implementation

* add class_weight and ignore_index; support different alpha values for different classes

* fixed some bugs

* fix bugs

* add comments

* modify test

* Update mmseg/models/losses/focal_loss.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* update test_focal_loss.py

* modified the implementation

* Update mmseg/models/losses/focal_loss.py

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>

* update focal_loss.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2021-12-03 00:18:40 -08:00
MengzhangLI 504a5c6bd2 [Doc] add MMHuman3D link #1101 2021-12-02 21:35:49 -08:00
MengzhangLI 6a2cfea73b [Feature] Support Real-time model ERFNet (#960)
* first commit

* Fixing Unittest Error

* first refactory of ERFNet

* Refactorying NonBottleneck1d Module

* uploading models&logs

* uploading models&logs

* fix partial bugs & typos

* ERFNet

* add ERFNet with FCNHead

* fix typos of ERFNet

* add name on README.md cover

* chane name to T-ITS'2017

* fix lint error
2021-12-01 23:54:39 -08:00
MengzhangLI defb21bf8a [Fix] Change the upper version of mmcv to 1.5.0 #1096 2021-12-01 21:16:23 +08:00
MengzhangLI 5f99f7d0f1 change LoveDA codalab server address (#1095) 2021-12-01 13:29:05 +08:00
MengzhangLI 78fbaaf179 0~ (#1090) 2021-11-30 23:03:50 +08:00
MengzhangLI 1cf6049758 change (#1083) 2021-11-30 20:54:25 +08:00
Kyungmin Lee 40b9ebb565 [Feature] Add Cutout transform (#1022)
* Fix typo in usage example

* [Feature] Add CutOut transform

* CutOut repr covered by unittests

* Cutout ignore index, test

* ignore_index -> seg_fill_in, defualt is None

* seg_fill_in is added to repr

* test is modified for seg_fill_in is None

* seg_fill_in (int), 0-255

* add seg_fill_in test

* doc string for seg_fill_in

* rename CutOut to RandomCutOut, add prob

* Add unittest when cutout is False
2021-11-30 20:37:06 +08:00
MengzhangLI c4a52a523c [Docs] Add abstract and image for every paper (#1060)
* add abstract and main figure

* add abstract and main figure
2021-11-30 20:34:45 +08:00
MengzhangLI ae8d5ff0d4 [Enhancement] CircleCI Setup (#1086)
* uploading circle-ci

* uploading circle-ci

* uploading circle-ci

* correct circleci folder

* change mmsegmentation to mmseg in config.yml

* adding timm package in circleci

* adding timm package in circleci

* fix original lint error
2021-11-30 00:25:35 -08:00
del-zhenwu 621114fa39 Skip CI on ignoring given paths (#1078)
* Skip CI on ignoring given paths

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix ignoring path with using

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>
2021-11-29 15:48:57 +08:00
Ebby 3525d35beb Update get_started.md (#1066)
Fix error in the chinese get_started file

完成的安装脚本 ==> 完整的安装脚本
2021-11-27 03:51:01 +08:00
Junjun2016 341ecc7633 [Enchance] Set a random seed when the user does not set a seed. (#1039) 2021-11-26 10:55:15 +08:00
MengzhangLI fdc054614c [Fix] Fix Dataset Display on README.md (#1072)
* fix dataset display on readme

* delete pytorch1.3.1

* change PyTorch 1.5.1 to 1.5or1.5.0

* change PyTorch 1.5.1 to 1.5.0

* change PyTorch 1.5.1 to 1.5.0

* fix cu102
2021-11-25 09:40:29 -08:00
Kingdrone 48d4222412 [Feature] Support LoveDA dataset (#1028)
* update LoveDA dataset api

* revised lint errors in dataset_prepare.md

* revised lint errors in loveda.py

* revised lint errors in loveda.py

* revised lint errors in dataset_prepare.md

* revised lint errors in dataset_prepare.md

* checked with isort and yapf

* checked with isort and yapf

* checked with isort and yapf

* Revert "checked with isort and yapf"

This reverts commit 686a51d9

* Revert "checked with isort and yapf"

This reverts commit b877e121bb.

* Revert "revised lint errors in dataset_prepare.md"

This reverts commit 2289e27c

* Revert "checked with isort and yapf"

This reverts commit 159db2f8

* Revert "checked with isort and yapf"

This reverts commit 159db2f8

* add configs & fix bugs

* update new branch

* upload models&logs and add format-only

* change pretraied model path of HRNet

* fix the errors in dataset_prepare.md

* fix the errors in dataset_prepare.md and configs in loveda.py

* change the description in docs_zh-CN/dataset_prepare.md

* use init_cfg

* fix test converage

* adding pseudo loveda dataset

* adding pseudo loveda dataset

* adding pseudo loveda dataset

* adding pseudo loveda dataset

* adding pseudo loveda dataset

* adding pseudo loveda dataset

* Update docs/dataset_prepare.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* Update docs_zh-CN/dataset_prepare.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* Update docs_zh-CN/dataset_prepare.md

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* Delete unused lines of unittest and Add docs

* add convert .py file

* add downloading links from zenodo

* move place of LoveDA and Cityscapes in doc

* move place of LoveDA and Cityscapes in doc

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-11-24 19:41:19 +08:00
MengzhangLI 7e5e34b217 add MMFewShot on README (#1065) 2021-11-24 19:40:00 +08:00
MengzhangLI 765a3a117a add mmflow on README (#1052) 2021-11-18 21:57:30 +08:00
MengzhangLI b692ab740c [Benchmark] Add BiSeNetV1 COCO-Stuff 164k benchmark (#1019)
* bisenetv1 on cocostuff164k

* change config_names & delete redundant keys

* pretrain should before lr.

* remove redundancy in bisenetv1_r50-d32
2021-11-17 00:12:02 -08:00
MengzhangLI 6d88b07084 fixing dice metric in unet (#1041) 2021-11-16 20:14:17 +08:00