* 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

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

* change version to v0.21.0

* change version to v0.21.0

* change version to v0.21.0

* change version to v0.21.0

* 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//

* change version to v0.20.0

* change version to v0.20.0

* change version to v0.20.0

* First commit for video demo

* fix lint

* update

* fix

* add wget in shell

* change version to v0.19.0

* update changelog

* bump to v0.18.0

* replace \ with /

* Improve docs style

* update lists

* update the size of image

* modify duplicate mmdet3d

* [Fix] Convert SyncBN to BN when training on DP.

* Modify SyncBN2BN.

* Add SyncBN2BN unit test.

* Resolve some comments.

* use mmcv official revert_sync_batchnorm

* Remove local syncbn2bn unit tests.

* Update mmcv version.

* Fix bugs of gather model tools.

* Modify warnings.

* Modify docker mmcv version.

* Update mmcv version table.

* Bump to v0.16.0

* fix doc

* fix changelog

* fix changelog

* Bump to v0.15.0

* fixed version

* fix mmcv version compatible

* update version compatible

Co-authored-by: hejunjun <hejunjun@pjlab.org>

* refactor docs

* add docs

* add modelzoo

* refactor getting started

* [Improvement] Add markdown linter and fix linting errors

* fixed pip

* Windows basic support

* getting_started updated for Windows.

* add experimental

* install.md restructured to seperate Windows & Linux.

* fix problems in install.md

* fix mmcv version problem.

* Fix fastscnn resize problems. (#82)

* Fix fast_scnn resize problems

* Fix fast_scnn resize problems 1

* Fix fast_scnn resize problems 2

* test for pascal voc

* [Doc] Add annotaion format note (#77)

* update pytorch version to 1.6.0 in install.md

* del fastscnn_pascal config

* del create_symlink=True

* Merge instructions for Linux & Windows

* mmcv version updated

* redundant newline deleted

* Update docs/install.md

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

* Update docs/install.md

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

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

* Auto get version info and git hash

* bump 0.5.1 and update doc

* fixed docs

* Add change log

* fixed name in pypi, add badge

* fixed name in install.md

* update install.md

* add pypi deployment

* remove useless jobs

* fixed typo and cleanup

* delete build.tx

* add change log

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