[Refactor] Add SegDataSample

See merge request openmmlab-enterprise/openmmlab-ce/mmsegmentation!9

[Refactor] Refactor all registries

See merge request openmmlab-enterprise/openmmlab-ce/mmsegmentation!3

[Refactory] Clean UTs

See merge request openmmlab-enterprise/openmmlab-ce/mmsegmentation!2

* [WIP] Data configuration

* [Doc] Add data configuration

* version info

* grammar

* typo

* typo

* format

* fix based on comments

* grammar

* comments

* [Enhancement] Delete DS_Store file

* [Enhancement] Fix the build_segmentor

* [Enhancement] Delete DS_Store file

* [Enhancement] Delete DS_Store file

* Bump version to v0.24.1

* version.py

* changelog.md

* fix docstring

* fix ut for optimizer cosntructor

* 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>

* [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>

* [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>

* [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>

* [Fix] Fix system dependencies in CI

* del pt1.5

* add gpg keys

* add pt1.5

* [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>

* [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>

* [Refactor] Add build_pos_embed and build_layers for BEiT

* Update mmseg/models/backbones/beit.py

* 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>

* [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

* [fix] cfg dir in colab

* Update demo/MMSegmentation_Tutorial.ipynb

We are going to use a new blob account to store the checkpoints.

* 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>

* [WIP]Update checkpoint for model in deeplabv3plus

* add aug test

* url fix

* [Enhancement] MMCV maximum_version set to 1.6

* [Enhancement] MMCV maximum_version set to 1.6

* [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>

* [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

* [Fix] Input previous results for the latter cascade_decode_head

* minors