* Support #1375: add demo/image_demo.py support for STARE

* Update mmseg/core/evaluation/class_names.py

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

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

* Update get_flops.py

argparse.ArgumentParser(description='Get the FLOPs of a segmentor')

* Update get_flops.py

* [Feature] add nlc2nchw2nlc and nchw2nlc2nchw

* add example

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

typos

* 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 typos

* [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

* change version to v0.22.0

* change version to v0.22.0

* add mmcls version in get_started.md

* add mmcls installation and move PR1299 into enhancement

* add mmcls installation and move PR1299 into enhancement

* remove MMCLS and make mmcv <=1.5.0 version in get_started.md

* fix typo

* 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

* generate and plot confusion matrix

* fix typo

* add usage and examples for confusion matrix

* deal with nan values(pick pr#7147 mmdet)

* fix md format

[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

* fix export onnx inference difference type Cast error

* fix export onnx inference difference type Cast error.

* use yapf format

* use same device type with pairwise_weight

* [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 unnecessary docstrings

* modify comments in self._forward_feature()

* modify docstrings in self._forward_feature()

* fix docstring

* modify uperhead

* Add deprecation message for deploy tool

* deploy test

* 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

* [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

* 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 <mcmong@pku.edu.cn>

* [Fix] Fix the bug that setr cannot load pretrain

* delete new pretrain

* 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

fix wrong file format. it should be png instead of jpg

* Update the installation of MMCV

* use matrix.torch_version

* fix typo in doc

* fix docs

* fix colab

* change docs

* make accuracy take into account ignore_index

* add UT for accuracy

* Bump v0.21.1

* add improvements in changelog

* add improvements in changelog

* fix cn readme

* change changelog

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

* fixed linting

* [Improve] Use MMCV load_state_dict func in ViT/Swin

* use CheckpointLoader instead