* restructure unit tests

* fix paths

* doc: Update install.md

add `conda install Cython` before install the forked version of `pycocotools`

* add cython to requirements/build.txt

Co-authored-by: Kai Chen <chenkaidev@gmail.com>

* fix isort issue

* limit isort version to 4.3.21

* add --recursive back for isort

* update docstring formats

* fix :func:

* minor update

* change accuracy to positive recall in FSAF

* use mmdet accuracy module to calculate pos recall in fsaf

* Change label to long in unittest

* revise docstring according to comments

* revise docstring according to comments

* Add transform types todo

* Move TODO to Line15

* Bump to 2.2

* remove some

* update

* update

* update mmcv version

* add switch in loading, fix scale_factor bug

* add unittest for MultiScaleFlipAug and Resize

* fix unittest for test_loading.py

* move default_meta_key to Bundle, add aug test for Cascade RCNN/Mask RCNN/HTC

* update Bundle and add unittest, update original unittest

* fix yapf formatting

* fix the version of codecov-action to 1.0.7

Co-authored-by: Kai Chen <chenkaidev@gmail.com>

* Complete model zoo models

* Update performance

* Update links

* Update gfl aws links

* Update groie performance

* Complete model zoo models

* Update performance

* Update links

* refactor anchor free detector

* add doc str

* fix fovea

* make consistent with previous version

* fix format

* fix format

* add version

* fix k and p

* WIP: add auto augmentation

* add blank space

* change AutoAugment based on 1-st comments

* fix a bug in AutoAugment

* use Compose in AutoAugment

* move Compose from __call__ to __init__ in AutoAugment

* change AutoAugment based on 2nd comments

* fix a typo in AutoAugment

* Add support for DetectoRS.

* Fix Travis CI build failure and remove loading rfp_pretrained for test

* Revise the code according to the PR reviews:

* remove unnecessary `,`

* add docstring to ASPP and ConvAWS2d

* make args of ASPP configurable

* simplify the code of ConvAWS2d

* import nn and functional for SAConv2d

* rewrite rfp_conv with build_conv_layer and constant_init

* rename rfp_inp with rfp_inplanes

* reformat code to pass Travis CI build

* Revise codes according to the PR reviews:

* Create new backbone DetectoRS_ResNe(X)t to incorporate RFP and SAC.

* Initialize modules with mmcv.cnn.

* Revise the codes of RFP.

* Revise codes according to the PR comments:

* Add docstrings to Bottleneck in mmdet/models/backbones/detectors_resnet.py.

* Add docstrings to _load_from_state_dict in mmdet/ops/conv_ws.py.

* Initialize the switch of SAC with mmcv.

* minior refactor and docstring

* update doc

* update README

* move init into init_weights()

* update model zoo

* add gfl

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

* add gfocal losses

* add gfl head, its related code, configs

* fix 2x config bug

* add most model and log in gfl README

* update gfl model and log

* Update transforms.py

modify variables  L, T, R, B   to  left, top, right, bottom

* Update gfocal_loss.py

modify variables into meaningful names:
* pt -> scale_factor
* a -> pos   b -> pos_label
* disl -> dis_left  disr -> dis_right
* wl -> weight_left  wr -> weight_right

* Update gfocal_loss.py

update formats

* remove duplicated get_bboxes/IoU calculation, make QFL consistent

* add all docstring in gfl_head.py and gfocal_loss.py

* add RandomCenterCropPad and unittest

* add instruction for RandomCenterCropPad

* update Resize, RandomCenterCropPad and MultiScaleFlipAug

* update unittest of Resize

* update docstring

* add unittest for MultiScaleFlipAug with Resize

* update function _get_border

* update __init__ and __repr__, fix unittest

* fix repr_str

* add docstrings

* update docstring

* Update transforms.py

* add assert in Resize

* fix linting error

* rename regnet configs

* Further fix bugs

* Update 400MF

* fix name bugs in configs

* fix bn default

* migrate to github action

* fixed typo

* install pycocotools

* resolve comments

* fixed syntax

* add interrogate to travis

* add missing requirements

* migrate flops counter to mmcv

* remove useless unit tests

* update the doc

* add docstring for pipelines

* add docs string for transform pipeline

* add dataset docs

* resovle comments

* refactor table

* resovle comments

* delete __repr__

* resolve comments

* minor update

* update readme

* minor update

* rename api

* Add PointRend

* remove PointExtractor

* add 1x 3x mstrain

* fixed test

* fixed test bug

* add README.md

* fixed doc string

* update doc

* update doc

* update comments

* fixed docs

* update docs

* change roi extractor

* update docstring

* minior update

* update docstring

* rename to mask point head

* simplify super

* move point head

* rename

* add doc

* fix some typos

* fix some doc

* fix property doc

* update doc

* complete free anchor doc

* Code for paper "Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training"

* update configs/dynamic_rcnn/dynamic_rcnn_r50_fpn_1x.py

* reformat code

* simplify code

* update model link

* simplify code

* simplify code logic

* simplify code and add comments

* minor updates of the docstring

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

* Add docstrings of core modules and methods

* Update docs and fix comments

* Complete docstrings

* Resolve comments

* reformat docstrings

* resolve comments

Rename faster_rcnn_regnetx-3GF_fpn_mstrxin_3x_coco.py to faster_rcnn_regnetx-3GF_fpn_mstrain_3x_coco.py (#3126)

Fix potential typo

* add voc benchmark

* add faster rcnn voc res