* [Fix] Fix SegLocalVisualizer gt_sem_seg cuda tensor error

* fix ut error and add config visualizer dict

* fix ut error

* [Feature] Add SegVisualizer

* change name to visualizer_example

* fix inference api

* fix video demo and refine inference api

* fix

* mmseg compose

* set default device to cuda:0

* fix import

* update dir

* rm engine/visualizer ut

* refine inference api and docs

* rename

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

* [Feature] Add SegVisualizer

* change name to visualizer_example

* fix typo

* refactor folder structure

* add load image from ndarray pipeline

* fix import

* [Fix] Fix register_all_modules and imports

* fix transforms import

[Fix]Add label_map and reduce_zero_label in metainfo of dataset and deprecate reduce_zero_label in load annotation

* fix docstring

* fix ut for optimizer cosntructor

* [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>

* 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>

* [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

* add with cp to mit and vit

* add test unit

Co-authored-by: jiangyitong <jiangyitong1@sensetime.com>

* [Fix] Add avg_non_ignore in cross entropy loss

* [Fix] Add avg_non_ignore in cross entropy loss

* add docstring

* fix ut

* fix docstring and comments

* fix

* fix bce

* fix avg_factor in BCE and add more ut

* add avg_non_ignore

* add more ut

* fix part of ut

* fix part of ut

* test avg_non_ignore would not affect ce/bce when reduction none/sum

* test avg_non_ignore would not affect ce/bce when reduction none/sum/mean

* re-organize ut

* re-organize ut

* re-organize ut

* re-organize hardcode case

* fix parts of comments

* fix another parts of comments

* fix

* [Feature] Add BEiT backbone

* fix

* fix

* fix

* fix

* add readme

* fix

* fix

* fix

* fix

* fix

* add link

* fix memory

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix test_beit.py

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* [Feature] add nlc2nchw2nlc and nchw2nlc2nchw

* add example

* add test, add **kwargs to make it more universal

* knet first commit

* fix import error in knet

* remove kernel update head from decoder head

* [Feature] Add kenerl updation for some decoder heads.

* [Feature] Add kenerl updation for some decoder heads.

* directly use forward_feature && modify other 3 decoder heads

* remover kernel_update attr

* delete unnecessary variables in forward function

* delete kernel update function

* delete kernel update function

* delete kernel_generate_head

* add unit test & comments in knet.py

* add copyright to fix lint error

* modify config names of knet

* rename swin-l 640

* upload models&logs and refactor knet_head.py

* modify docstrings and add some ut

* add url, modify docstring and add loss ut

* modify docstrings

* [Fix] Fix the bug that when all pixels in an image is ignored, the accuracy calculation raises ZeroDivisionError

* use eps

* all close

* add ignore test

* add eps

* upload original backbone and configs

* ConvNext Refactor

* ConvNext Refactor

* convnext customization refactor with mmseg style

* convnext customization refactor with mmseg style

* add ade20k_640x640.py

* upload files for training

* delete dist_optimizer_hook and remove layer_decay_optimizer_constructor

* check max(out_indices) < num_stages

* add unittest

* fix lint error

* use MMClassification backbone

* fix bugs in base_1k

* add mmcls in requirements/mminstall.txt

* add mmcls in requirements/mminstall.txt

* fix drop_path_rate and layer_scale_init_value

* use logger.info instead of print

* add mmcls in runtime.txt

* fix f string && delete

* add doctring in LearningRateDecayOptimizerConstructor and fix mmcls version in requirements

* fix typo in LearningRateDecayOptimizerConstructor

* use ConvNext models in unit test for LearningRateDecayOptimizerConstructor

* add unit test

* fix typo

* fix typo

* add layer_wise and fix redundant backbone.downsample_norm in it

* fix unit test

* give a ground truth lr_scale and weight_decay

* upload models and readme

* delete 'backbone.stem_norm' and 'backbone.downsample_norm' in get_num_layer()

* fix unit test and use mmcls url

* update md2yml.py and metafile

* fix typo

[Feature] Add `min_size` arg in `Resize` to keep the shape after resize bigger than slide window (#1318)

* [Feature] add setr_resize

* fix a bug

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix