Commit Graph

515 Commits (46723a954397b5ca351b7910d4e36f54e071923b)
 

Author SHA1 Message Date
zhengmiao 619bc4a185 Merge branch 'limengzhang/refactor_SegDataSample' into 'refactor_dev'
[Refactor] Add SegDataSample

See merge request openmmlab-enterprise/openmmlab-ce/mmsegmentation!9
2022-05-16 11:31:47 +00:00
limengzhang.vendor 30d75b75eb [Refactor] Add SegDataSample 2022-05-16 11:31:46 +00:00
zhengmiao 168c8831dd Merge branch 'linfangjian/refactor_registies' into 'refactor_dev'
[Refactor] Refactor all registries

See merge request openmmlab-enterprise/openmmlab-ce/mmsegmentation!3
2022-05-10 12:15:20 +00:00
linfangjian.vendor 7a32d610e4 [Refactor] Refactor all registries 2022-05-10 12:15:20 +00:00
zhengmiao b2abe15787 Merge branch 'zhengmiao/tests_bp' into 'refactor_dev'
[Refactory] Clean UTs

See merge request openmmlab-enterprise/openmmlab-ce/mmsegmentation!2
2022-05-09 10:29:38 +00:00
zhengmiao 35c695bba7 [Refactory] Clean UTs 2022-05-09 10:29:38 +00:00
linfangjian01 24cc27ddd5 add ruby in .pre-commit-config.yaml 2022-05-09 12:21:47 +08:00
Miao Zheng df70f55639 [Doc] Add explanation and usage instructions for data configuration (#1548)
* [WIP] Data configuration

* [Doc] Add data configuration

* version info

* grammar

* typo

* typo

* format

* fix based on comments

* grammar

* comments
2022-05-06 15:25:05 +08:00
MengzhangLI 799486e124 [Fix] Fix main line link in MAE README.md (#1556) 2022-05-05 17:49:38 +08:00
Miao Zheng 9b3338fa2b [Enhancement] Fix the build_segmentor in colab demo (#1551)
* [Enhancement] Delete DS_Store file

* [Enhancement] Fix the build_segmentor
2022-05-05 13:39:56 +08:00
Miao Zheng 4630918795 [Enhancement] Delete DS_Store file (#1549)
* [Enhancement] Delete DS_Store file

* [Enhancement] Delete DS_Store file
2022-05-04 19:49:23 +08:00
Miao Zheng e18e549792 [Enhancement] Use round-robin (#1543) 2022-05-03 17:12:19 +08:00
MengzhangLI 7f1a72ac42 Bump version to v0.24.1 (#1541)
* Bump version to v0.24.1

* version.py

* changelog.md
2022-05-01 14:06:04 +08:00
Miao Zheng 28b42597a1 [Enhancement]Revise docstring and UT for layer decay LR (#1540)
* fix docstring

* fix ut for optimizer cosntructor
2022-05-01 13:13:53 +08:00
Sebastian 9bc82388bc Replace Arxiv with ICCV bibtex entry (#1536)
* Replace Arxiv with ICCV bibtex entry

* Update configs/segmenter/README.md

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-05-01 12:56:56 +08:00
FangjianLin 40ae7edd49 [Fix] Add MAE LayerDecayOptimizerConstructor (#1539) 2022-05-01 12:42:49 +08:00
Miao Zheng f33b7cafc8 Bump version to v0.24.0 (#1533)
* [WIP] Bump version to v0.24.0

* changelog

* Update docs/en/changelog.md

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

* Update docs/en/changelog.md

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

* Update docs/en/changelog.md

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

* Update docs/en/changelog.md

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

* Update docs/en/changelog.md

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

* Update docs/en/changelog.md

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

* words

* typo

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-04-29 22:23:02 +08:00
wangbin 578d4d0c42 [Fix] Fix the bug in binary_cross_entropy (#1527)
* [Fix] Fix the bug in binary_cross_entropy

 Fix the bug in binary_cross_entropy
'label.max() <= 1' should mask out ignore_index, since the ignore_index often set as 255.

* [Fix] Fix the bug in binary_cross_entropy, add comments

As the ignore_index often set as 255, so the binary class label check should mask out ignore_index.

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* [Fix] Fix the bug in binary_cross_entropy

As the ignore_index often set as 255, so the binary class label check should mask out ignore_index.

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Co-authored-by: MeowZheng <meowzheng@outlook.com>
2022-04-29 19:32:12 +08:00
Miao Zheng d0955901b6 [Fix] Add GPG keys and del mmcv version in Dockerfile (#1534) 2022-04-29 19:31:50 +08:00
MengzhangLI e9bfabe434 [Doc] Add more clearly statement of CPU training/inference (#1518)
* [Doc] Add more clearly statement of CPU training/inference

* Update docs/en/inference.md

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
2022-04-29 16:41:32 +08:00
Miao Zheng f06c39f9d6 [Fix] Add GPG keys in CI (#1532)
* [Fix] Fix system dependencies in CI

* del pt1.5

* add gpg keys

* add pt1.5
2022-04-29 14:20:08 +08:00
MengzhangLI 53573dd5a9 [Fix] Add MAE in cover page (#1523) 2022-04-28 21:54:57 +08:00
Miao Zheng 0644b3cd30 [Enhancement] Delete seed in dist_train.sh (#1519) 2022-04-28 11:35:10 +08:00
Yuan Liu 2b2d09d491 [Feature]: Add MAE (#1307)
* [Fix]: Fix lint

* [WIP]: Add mae seg config

* [Feature]: Add MAE seg

* [Fix]: Fix mae dataset img scale bug

* [Fix]: Fix lint

* [Feature]: Change mae config to mae_segmentation's config

* [Feature]: Add interpolate pe when loading

* [Fix]: Fix pos_embed not used bug

* [Fix]: Fix lint

* [Fix]: Init rel pos embed with zeros

* [Fix]: Fix lint

* [Fix]: Change the type name of backbone to MAE

* [Fix]: Delete ade20k_512x512.py

* [Fix]: Use mmseg provided ade20k.py

* [Fix]: Change 1 sample per gpu to 2 samples per gpu

* [Fix]: Fix conflict

* [Refactor]: Use the TransformerEncoderLayer of  BEiT

* [Feature]: Add UT

* [Fix]: Change the default value of qv bias to False

* [Fix]: Initialize relative pos table with zeros

* [Fix]: Delete redundant code in mae

* [Fix]: Fix lint

* [Fix]: Rename qkv_bias to qv_bias

* [Fix]: Add docstring to weight_init of MAEAttention

* [Refactor]: Delete qv_bias param

* [Fix]: Add reference to fix_init_weight

* [Fix]: Fix lint

* [Fix]: Delete extra crop size

* [Refactor]: Rename mae

* [Fix]: Set bias to True

* [Fix]: Delete redundant params

* [Fix]: Fix lint

* [Fix]: Fix UT

* [Fix]: Add resize abs pos embed

* [Fix]: Fix UT

* [Refactor]: Use build layer

* [Fix]: Add licsense and fix docstring

* [Fix]: Fix docstring

* [Feature]: Add README metafile

* [Fix]: Change 640 to 512

* [Fix]: Fix README

* fix readme of MAE

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-04-28 00:54:50 +08:00
Yuan Liu 43b8a1d8dc [Feature]: Add MAE (#1307)
* [Fix]: Fix lint

* [WIP]: Add mae seg config

* [Feature]: Add MAE seg

* [Fix]: Fix mae dataset img scale bug

* [Fix]: Fix lint

* [Feature]: Change mae config to mae_segmentation's config

* [Feature]: Add interpolate pe when loading

* [Fix]: Fix pos_embed not used bug

* [Fix]: Fix lint

* [Fix]: Init rel pos embed with zeros

* [Fix]: Fix lint

* [Fix]: Change the type name of backbone to MAE

* [Fix]: Delete ade20k_512x512.py

* [Fix]: Use mmseg provided ade20k.py

* [Fix]: Change 1 sample per gpu to 2 samples per gpu

* [Fix]: Fix conflict

* [Refactor]: Use the TransformerEncoderLayer of  BEiT

* [Feature]: Add UT

* [Fix]: Change the default value of qv bias to False

* [Fix]: Initialize relative pos table with zeros

* [Fix]: Delete redundant code in mae

* [Fix]: Fix lint

* [Fix]: Rename qkv_bias to qv_bias

* [Fix]: Add docstring to weight_init of MAEAttention

* [Refactor]: Delete qv_bias param

* [Fix]: Add reference to fix_init_weight

* [Fix]: Fix lint

* [Fix]: Delete extra crop size

* [Refactor]: Rename mae

* [Fix]: Set bias to True

* [Fix]: Delete redundant params

* [Fix]: Fix lint

* [Fix]: Fix UT

* [Fix]: Add resize abs pos embed

* [Fix]: Fix UT

* [Refactor]: Use build layer

* [Fix]: Add licsense and fix docstring

* [Fix]: Fix docstring

* [Feature]: Add README metafile

* [Fix]: Change 640 to 512

* [Fix]: Fix README

* fix readme of MAE

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-04-28 00:54:20 +08:00
Miao Zheng d90e700284 [Refactor] Add build_pos_embed and build_layers for BEiT (#1517)
* [Refactor] Add build_pos_embed and build_layers for BEiT

* Update mmseg/models/backbones/beit.py
2022-04-27 11:37:03 +08:00
FangjianLin 7c3bf22885 [Refactory] Merge BEiT and ConvNext 's LR decay optimizer constructors (#1438)
* move layer_decay_optimizer_constructor

* fix

* fix

* merge test_core

* fix

* add DeprecationWarning

* fix DeprecationWarning

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix test

* fix

* fix

* fix

* fix

* fix ut

* fix

* fix

* Update tests/test_core/test_layer_decay_optimizer_constructor.py

* fix

* fix

* fix

* fix

Co-authored-by: MeowZheng <meowzheng@outlook.com>
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
2022-04-27 10:43:25 +08:00
Miao Zheng 42fc9dfba0 [Fix] Revise high workers_per_gpus (#1506) 2022-04-25 13:19:47 +08:00
Miao Zheng f64c7c331b [Refactor] Refactor transfomer encode layer in ViT and BEiT backbone (#1481)
* [Refactor] Refactor transfomer encoder layer

* fix ffn cfg

* fix drop path cfg

* private init func

* fix qv bias

* fix qkv bias

* fix qkv bias

* wH->Wh
2022-04-23 17:35:05 +08:00
Miao Zheng d7bf706a3f [Fix] the directory of cfg file in colab demo (#1501)
* [fix] cfg dir in colab

* Update demo/MMSegmentation_Tutorial.ipynb
2022-04-23 15:00:31 +08:00
Li Dong 1c060ba2ae migrate azure blob for beit checkpoints (#1503)
We are going to use a new blob account to store the checkpoints.
2022-04-23 14:57:32 +08:00
Mladen Fernežir 9e17a0d364 Fix validation loss logging (#1494) 2022-04-22 15:25:32 +08:00
jere357 aa68bf15b7 fixed a couple of issues that made the notebook not work in colab (#1460)
* fixed a couple of issues that made the notebook not work in colab

i fixed a couple of issues that made the notebook not work in colab 
1. it downloaded incompatible versions of pytorch and cuda + the conda command doesnt do anything in colab since there is no conda in colab idk w y wanna do about that - The commit of 2 days ago only changes the conda command version and not the pip command which is used while isntaling mcvv
2. /demo.png doesnt exist in colab so i added a wget to download some cityscapes photo from the internet and run inference on that photo
3. i think it would be optimal to have 2 notebooks. 1 for running locally when cloning your git branch and one to run in google colab.

* Update demo/MMSegmentation_Tutorial.ipynb

* Update demo/MMSegmentation_Tutorial.ipynb

* Update demo/MMSegmentation_Tutorial.ipynb

* Update demo/MMSegmentation_Tutorial.ipynb

* Update demo/MMSegmentation_Tutorial.ipynb

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
2022-04-22 10:10:02 +08:00
Miao Zheng 10c0c24638 [Enhancement]Update checkpoint for model in deeplabv3plus (#1487)
* [WIP]Update checkpoint for model in deeplabv3plus

* add aug test

* url fix
2022-04-21 20:15:34 +08:00
Wang Xinjiang b5d8c7dc6c Fix potential bugs in accuracy.py (#1496) 2022-04-21 10:18:37 +08:00
Miao Zheng 464ebab53e [Enhancement] MMCV maximum_version set to 1.6 (#1480)
* [Enhancement] MMCV maximum_version set to 1.6

* [Enhancement] MMCV maximum_version set to 1.6
2022-04-19 16:19:56 +08:00
FangjianLin e4b3604e50 [Fix] Register optimizer constructor with mmseg (#1456)
* [fix] register optimizer onstructor with mmseg

* fix lint

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* Update tests/test_core/test_optimizer.py

* Update tests/test_core/test_optimizer.py

* Update tests/test_core/test_optimizer.py

* Update tests/test_core/test_optimizer.py

* fix lint

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
2022-04-16 16:45:17 +08:00
MengzhangLI 4b15d558c2 [Fix] Update .owners.yml (#1477) 2022-04-15 17:44:49 +08:00
Rockey 23b7cfc59d [Fix] Support single cahnnel `pred` for Binary Cross Entropy Loss (#1454)
* [Fix] Fix the bug that binary cross entropy loss doesn't support single channel input

* imcrease coverage

* modify implementation

* increase coverage

* add assert

* modify implementation

* enshollow condition judge

* fix
2022-04-14 11:26:02 +08:00
Miao Zheng cc3a0528fe [Fix] Input previous results for the last cascade_decode_head (#1450)
* [Fix] Input previous results for the latter cascade_decode_head

* minors
2022-04-13 21:16:29 +08:00
Miao Zheng f50bfe3e3d [Enhance] Add extra dataloader settings in configs (#1435)
* [Enhance] Add extra dataloader settings in configs

* val default samples

* val default samples

* del unuse

* del unused
2022-04-13 13:30:10 +08:00
panfeng-hover add835be3f Avoid converting label ids twice by label map during evaluation (#1417)
* Avoid converting label ids twice by label map during evaluation

* Update mmseg/datasets/custom.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* lint

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Co-authored-by: MeowZheng <meowzheng@outlook.com>
2022-04-12 18:26:25 +08:00
Miao Zheng a09df2c39d [Fix] inconsistent dtype ofseg_label in stdc decode (#1463) 2022-04-10 14:18:16 +08:00
Pan Zhang cba10b3f15 [fix] fix image save path bug in Windows (#1423)
* [fix] fix image save path bug in Windows

* fix lint error
2022-04-09 21:17:51 +08:00
Yzichen f45ddc97bb fix bug about label_map (#1445)
* fix bug about label_map

* Update mmseg/datasets/pipelines/loading.py

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

* lint

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
Co-authored-by: MeowZheng <meowzheng@outlook.com>
2022-04-09 21:11:47 +08:00
Andrey 9619deddef [Fix] MMSegmentation Tutorial running on colab error fix (#1452)
* update pytorch and cudatoolkit versions for colab

Previous version was throwing an error after calling for mmseg.apis import (line 147) due to incompatible cudatoolkit version in colab.

* Update description about versions used
2022-04-06 22:04:37 +08:00
Miao Zheng 4bc2a30ea0 Add DistSamplerSeedHook for when runner is EpochBasedRunner (#1449)
* Add DistSamplerSeedHook for when runner is EpochBasedRunner

* add comment
2022-04-06 22:04:11 +08:00
MengzhangLI 549616888e [Fix] Fix bug in `tools/analyse_logs.py` caused by wrong plot_iter in some cases. (#1428)
* fix_analyze_logs

* fix comments

* fix comments
2022-04-05 12:47:41 +08:00
MengzhangLI 2a3083462e [Feature] Provide URLs of Swin Transformer pretrained models (#1389)
* [Feature] Provide URLs of Swin Transformer pretrained models

* [Feature] Add multi machine `dist_train`. (#1383)

* Add training startup documentation

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* delete pretrained=None in all six config files

* [Fix] make arguments effective in tools/confusion_matrix.py (#1401)

* add an argument for customizing `title' of the output figure

* fix `color_theme' arguments not passing to plot function

Signed-off-by: code14 <mob5566@gmail.com>

* colab notebook: fix outdated link for doc (#1392)

* colab notebook: fix outdated link for doc

Fixed outdated link for how to customize your datasets by reorganizing data.

* fix lint

* fix typo (#1405)

* [Fix] Fix windows-style path in `md2yml.py` in Windows pre-commit.  (#1407)

* test

* avoid windows path

* [Fix] fix the config name style description (#1414)

Co-authored-by: FangjianLin <93248678+linfangjian01@users.noreply.github.com>
Co-authored-by: Cody Wong <mob5566@gmail.com>
Co-authored-by: Nemo Xiong <xiongnemo@126.com>
Co-authored-by: Xiangxu-0103 <xuxiang0103@gmail.com>
Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com>
2022-04-05 11:36:38 +08:00
MengzhangLI df47283dc3 [Feature] Support Resnet strikes back (#1390)
* [Feature] Support Resnet strikes back

* fix url

* [Feature] Add multi machine `dist_train`. (#1383)

* Add training startup documentation

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* modify R-50b rsb

Co-authored-by: FangjianLin <93248678+linfangjian01@users.noreply.github.com>
2022-04-05 11:34:53 +08:00