* fix parrots compatibility

* add comments

* masks from (n,h,w) to [(h,w),...,(h,w)]

* Update transforms.py

* Update transforms.py

* forward compatible

* upgrade yapf

* minon clean

Co-authored-by: Cao Yuhang <yhcao6@gmail.com>

* update

* clip border

* clip border

* clip

* update

* update

* update

* update

* clamp neg probability in freeanchor

* refactor

* resolve comments

* Speedup expand when meets large image

* fix lint error

* Update transforms.py

* fix pytorch 1.7 imcompatibility issues

* remove useless files

* Make yoloV3 raw export work with TensorRT

* Change bool indexing to integer indexing

* Add comments to changes

* Add comments to changes

Co-authored-by: Daniel Suess <daniel@dsuess.me>

* add tpfp func

* fix docstring

* Resolve comments

`num_classes` in model should be the same as the number of dataset class

* update trouble shooting page to resolve segmentation fault

* resolve comments

* add faster rcnn C5

* add trained faster rcnn C5 model url

* fix typos

* update based on 1-st comments

* update unittest for ChannelMapper

* small changes of ChannelMapper's docstring

* small changes of ChannelMapper's docstring

* [Enhancement] Refactor Q&A

* fix typo

* fix cudatoolkit

* rename

* resovle cmts

* reanme

* fixed yaml

* add link

* bump to v2.6.0

* update version requirements

* Add README.md reference

* Fix README.md

Refactor documentation

* add rpn upgrade scripts for v2.5.0 compatibility

* rephrase docs

[Doc] Refactor doc on `tools/`

* add varifocal loss, vfnet head and config file

* fix nonzero() and register_module bug

* add more configs and README.md

* enlarge image in README.md

* add arxiv link

* add paper arxiv link

* attempt to fix checks error - res2net

* update readme

* update according to comments

* revert res2net.py

* compact the VFNetHead

* adapt for official TTA

* add unit tests and refine vfnet_head

* update url

* update readme

* add minor comments

* update supported models

* remove VFNet.png

Co-authored-by: Cao Yuhang <yhcao6@gmail.com>

Add docs

* Use mmdet.apis

* Add show_dir and show_score_thr args

* pre-commit

* Save each corruption in separate folder

* Save each corruption in separate folder

* speed up and improve stabe paa

* fix yapf

* change default value of covariance_type

* change precisions_init

* Add tied covariance type

* Change default covariance_type

Co-authored-by: d.rybalchenko <d.rybalchenko@visionlabs.ru>
Co-authored-by: rydenisbak <rydenisbak@mail.ru>