* Use build_runner in train api
* Support iter in eval_hook
* Add runner section
* Add test_eval_hook
* Pin mmcv version in install docs
* Replace max_iters with max_epochs
* Set by_epoch=True as default
* Remove trailing space
* Replace DeprecationWarning with UserWarning
* pre-commit
* Fix tests
* workflow: modify build, add deploy
* fix type: mmseg -> mmcls
* simplify build by delete cuda related settings
* re-sort requirements by pre-commit hook
* build: support more pytorch versions
* build: fix torchvision version bug
* del useless test imports
* merge upstream
* build: del docstring checking to pass coverage check