* Add upsample_cfg support in FPN

* small fix

* Add multiple extra conv sources

* small logical fix

* Add neck tests for fpn

* Add neck tests for fpn

* fixed several typos

* resolved issues

* Removed extra_convs_source option

* added necks to apis.rst

* change according to comments

* reconfigured configs

* save

* add retinanet and fix some inconsistent

* fix registry

* fix typos

* fix unmap bug

* fix some bugs

* clean

* minor fix

* fix k b

* add more cfgs

* fix detach

* add some benchmarks

* add some comments

* add more comments

* change test rpn proposal num

* add more models

* modify accroding comments

* more fix

* add pape link, fix some grammar error

* modify according to comments

* add unit test

* add unit tests for head

* fix some comments, add pape link

* add pisa roi head unittest

* fix README.md

* fix year

* use FileClient to replace mmcv.imread()

* typo fix

* rename file_client_cfg to file_client_args and bug fix

* add docstrings

* fix unittests

* fix unittests

* Use img_fields to handle same augmentation to multiple imgs

* Add unittest

* Fix unit tests

* Use basename

* Add ori_filename to img_metas

* Use ori_filename in test

* Update tests

* Add ori_filename to LoadMultiChannelImageFromFiles

* Add missing ori_filename in tests

* Add missing ori_filename in tests

* Add missing ori_filename

* Update model performance

* Update performance

* Fix unsaved change

* add conflict check

* Add RegNet, docs/refactor TBD

* Support RegNet

* Add RegNets

* Modify docs and refactor code

* fix pre-train bug

* Performance ready

* Use public model weights

* Performance & settings done

* Fix unittest bug

* Try another way of test config

* Add unittest and refactor

* Reformat

* Finish refactor regnet

* merge tests

* fix conflicts

* Fix resnext CI bug

* rename parameter

* Add ref link & clean _delete_

* tweaks of doc

* try resnext doctest

* add expansion in block

* remove doctest of resnext

* fix bug for coco person subset

('person') will be parsed as string.
It should be a tuple

* reformat

pass CI

* add res2net backbone

* add readme for res2net

* simplify res2net file

* remove some init in bottle2neck

* optimize forward code

* change init

* update results of res2net

* update config and readme

* add test and fix small issues

* add RepeatFactorDataset

* add docs and test

* rename to ClassBalancedDataset

* fixed typo

* update inf speed

* update some models

* update benchmark config and model

* add no aug config

* merge log model table with performance table

* add detectron2 url

* fix ms rcnn show

* fix show error when empty det

* Add links in docs

* Fix typo

* Add links of projects

* Add paper links

* Add test that fails on previous cpu implementation

* Fix nms cpu implementation

Results are now in order of their score

* Reformat code

* use mmcv nightly in travis

* fixed doc

* Add links in docs

* Fix typo

* Fix unittest bug

* adds note to remove build folder

* updates note to remove build folder

- CAMERA-ID was mention for image_demo.py

* Support class agnostic nms

* Allow filtering background

* Add class_agnostic as optional argument

* Previous approach was better

background is already filtered before batched_nms is called

* Add a mask rcnn example for config

* Add comments

* Add more comments

* Finish docs

* Fix refer

* Resolve comments

* resolve comments

* Fix indents

* Fix url

* Add benchmark gathering scripts

* Add auto test scripts

* Simplify assert

* Only push model gathering scripts

Co-authored-by: zww <zhangwenwei@sensetime.com>

* Add warnings

* Change according to comments

* Fix yapf

Co-authored-by: wangxinjiang <wangxinjiang@sensetime.com>

* compute pure inference time instead

* fix batch size

* fix batch size bug

* use img metas

* Delete file

* reformat

* fix yapl

* fix comments

* Changed the default num_pos to make fsaf loss without pos samples more robust

* moved avg_factor out of the for loop in fsaf_head

Co-authored-by: wangxinjiang <wangxinjiang@sensetime.com>

Fixes memory leak, resolves #2670

* Allow different stride in x and y direction

* Fix bugs, pass tests

* Added new test

* Added extra test

* Correct docs

* Update docs, only square SSD

* pass tests

* Rewrite test

* add python path in scripts

* Make python path work

* Shorter path

* Add docs

* Change dist scripts

* Change slurm example

* Fix validate default bug

* Change docs accordingly

settins -> settings

2. Added FSAF model zoo

Co-authored-by: wangxinjiang <wangxinjiang@sensetime.com>