* fix typo in doc

* update register

* also resolve #4334

* FPN deprecated warning

* FPN deprecated warning

* fix scale_factor is not same type as det_bboxes error

* Update model url from aws to aliyun

* Delete unnecessary changes

* update url

* add url link

* Test program

* Revert changes

* Update MMDet tutorial url

* FPN deprecated warning

* FPN deprecated warning

* Fix show_result error

* FPN deprecated warning

* FPN deprecated warning

* Fix scale_factor is not same type as det_bboxes error

* FPN deprecated warning

* FPN deprecated warning

* Delete mmdet.ops because it has been moved to mmcv

* add focal_loss in hungarian_assigner.py

* update hungarian_assigner.py

* update detr config

* update doc and codes

* fix unitest

* fix unitest

* modify code format

* update docstring

* fix unitest

* fix name

* fix docformat

* fix docformat

* fix format

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

* Code for Cascade RPN - NeurIPS 2019

* using mmdet2 apis

* update mmdet2 coords and minor fixes

* fix format

* update configs

* fix simple test

* update fast rcnn config

* minor fixes

* update docstring

* update readme

* update doc string

* minor fixes

* standard adaptive interface

* update agrs docs

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

* FPN deprecated warning

* FPN deprecated warning

* Fix empirical attention with resNext backbone error(#4228)

* Fix empirical attention in resnext backbone error

* Add test ResNeXt Bottleneck forward with plugins

* add FAQ doc in error-report

* resolve lint error

* fix #4181, invalid link in readme for maskrcnn cityscapes

* undo

* get the last epoch from config

* read eval metrics from the config key

* read the latest log from multiple logs

* use lower case of RESULTS_LUT

* handle evaluation key with VOC dataset case

* toy

* move the position of scipy import

* move the position of scipy import

* fix invalid link of config in faster_rcnn

* modify the count way of ckpts

* remove config statistics

* Add docstring for train.py/test.py/eval_metric.py

* Add docstring in the document

* Update docstring in the document

* Update docstring

* get the last epoch from config

* read eval metrics from the config key

* read the latest log from multiple logs

* use lower case of RESULTS_LUT

* handle evaluation key with VOC dataset case

* toy

* FPN deprecated warning

* FPN deprecated warning

* Update pretrain model url

* Fix pretrain model base url

* Add specific class pre-trained models

* Fix isort error

* Update doc description

* Update model url

* Rename config

* Rename config

* Fixed CI temporarily

* fixed torchvison

* fixed mmcv

* delete 1.4.0+cpu

* fix #4232, fix img_norm in hrnet when using fcos detector

* fix inherit in fcos_hrnetv2p_w32_gn-head_4x4_1x_coco.py

* re-benchmark all hrnet-based fcos models using fixes img_norm, and achieving higher performance

* [doc]: add doc for pytorch2onnx

* [doc]: remove blank lines

* resolve format of doc

* refact doc for pytorch2onnx

* add space

* add to index.rst

* FPN deprecated warning

* FPN deprecated warning

* Add the documentation of batch inference and test

* Add the documentation of options cfg and eval cfg

* Modify the document description

* Add doc description spacer

* Update doc description

* fix #4181, invalid link in readme for maskrcnn cityscapes

* undo

* fix #3950, avoid zero or too small value for new_beta

* make eps as global var

* go

* go

* go

* go

* remove unused

* Update trident_faster_rcnn.py

* fix nms for latest mmcv

* Delete tridentnet_r101_caffe_1x_coco.py

* fix ci

* Update tridentnet_r50_caffe_1x_coco.py

* add unit test

* Update test_backbones.py

* Update trident_roi_head.py

* add mstrain config

* update

* Update trident_roi_head.py

* Update trident_roi_head.py

* update accoding to comment

* Update trident_resnet.py

* update

* Update README.md

* Update README.md

* update

* Update trident_resnet.py

* Update tridentnet_r50_caffe_mstrain_1x_coco.py

* Update mmdet/models/backbones/trident_resnet.py

* Update resnet.py

* reformat to pass CI

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

* fix #4181, invalid link in readme for maskrcnn cityscapes

* undo

* fix #4181, invalid link in readme for maskrcnn cityscapes

* updating performance

* fix detr config for higher performance

* fix unit tests

* fix bug in distributed sampler

* add comments to explain the modification

* revise according to comments

* Add markdown lint in pre-commit hook

* add markdown lint

* FPN deprecated warning

* FPN deprecated warning

* update Readme of SABL

* update download link

* fix bug: PAFPN has no attribute extra_convs_on_inputs

* add on_lateral

* fix lint

* fix lint error

* support return indices when using nms

* support return indices when using nms

* support return indices when using nms

* support return indices when using nms

* Update gfl_head.py

There is a error in pytorch1.6 version when call reduce_mean in this head: input tensor is "int" format, can not call div_ direct. so, change it to float format.

* Update gfl_head.py