* add Localization Distillation for Object Detection https://arxiv.org/abs/2102.12252

* fix lint

* fix lint

* fix lint

* fix lint

* fix lint

* fix config

* add kd detector

* edit loss name

* overide setattr but failed

* move init_detector into init

* seperate ld and gfocal, fix unused param error

* small fix

* small fix

* add test, reload magic function, create kd_loss.py

* del teacher model warnings

* fix reference

* add ignored bbox test fix docstring

* small fix

* docstring fix

* change names

* fix

* fix

* fix test

* fix import

* fix

* docstring fix

* fix

* retest

* add test

* docstring fix

[Refactor]: Support batch inference traceable by ONNX in SSD, YOLOv3, FSAF, RetinaNet, and FCOS (#4699)

* Support batch infer in RetinaNet

* Suport batch multiclass_nms

* Revert multiclass_nms

* Fix api deprecated warning

* do not repeat anchors

* Move img_shapes

* Update Yolov3

* Support FCOS

* Support RPN

* Fix RPN topk_inds error

* make batch exportable to onnx for yolohead

* make fcos_head exportable to onnx with batch dim

* Support ATSS

* Support CornerNet and centripetalNet

* Update RetinaNet and delta_xywh

* Remove ugly code

* Remove ugly code of FCOS

* Remove ugly code of ATSS/YOLOV3

* Support RPN and revert bbox_head

* expand anchors to batch and remove BG class when use deploy_nms_pre

* Update

* Use dim=-1 instead of dim=2

* Rename anchor_head method

* Keep the original format output when nms is not use

* Rename method and unified code style

* Fix paa_head and unittest

* Fix FASF onnx export error

* Fix error

* fix single stage img_shapes for onnx

* move conf_thr

* fix rpn_head for onnx

* Add distance2bbox unittest

* Remove TODO

* Fix RPN

* Update docstrs

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

* add cfg

* add cfg

* fix typo

* fix pad

* fix test pad

* add readme

* modify by comments

* fix typo

* rpn head refactor

* guided anchor

* add deprecate warning

* add more warning for set ori augs

* fix unitest

* change base

* cascade rpn

* cornernet and centri

* grid frcnn ok

* ga anchor ok

* legacy ok

* pisa ok

* tridnet ok

* fix tutorals

* use ConfigDict

* Add type of runner in configs

* fix missing config

* support convert voc to cocoformat json

* modify according to comments

* sup customize runner

* fix typo

* use build runner

* minor fix

* modify according to comments

* add an assertion

* swap order

* fix tutorial

* Fix unittest

* Add COCO-Stuff docs

* Remove spaces

* Add paper conference link and mmcv install docs

* Update contributing

* fix num_classes and minor

* update converted models

Code for AAAI 2021 paper. "SCNet: Training Inference Sample Consistency for Instance Segmentation" (#4356)

* add scnet

* add more configs and minors

* fix unittest for scnet

* update docstring

* add forward test for htc and scnet

* fix build on pytorch 1.3 for empty tensor

* update doc string and minor refactor

* update unit-test and use inheritance for SCNet heads

* support scnet tta

* minor

* update readme

* minor fixes

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

* undo

* add config for paa_r50_fpn_mstrain_3x_coco.py

* reformat for CI building

* add config paa_r101_fpn_mstrain_3x_coco.py

* add r50 and r101 multiscale training 3x performance

* add pretrained model link

* add CompatibleCheckHook

* check val

* add docstr

* move hook to default runtime

* add unitest

* fix a typo

* fix unitest

* update docs

* add check for CLASSES is None

* fix doc

* Categorize tools

* Update docs

* Rename tools

* Tool organization

* Update README.md

* Update README.md

Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>

* use reduce pos and denorm

* add cfg

* fix cfg

* fix pt1.6

* update link

* clean

* add legacy cfg

* clean cfg

* update readme

* fix zero pos

* update url

* draft version train and test

* remove get_bbox in sparse_head

* refactor SparseRCNN model, align inference eval mAP with official repo

* add focal_loss in hungarian_assigner.py

* update hungarian_assigner.py

* update detr config

* update doc and codes

* fix unitest

* fix unitest

* add embedding_rpn and traing code

* modify code format

* fix proposalist in simpletest

* add focal loss traing

* fix acc

* fix reduce mean

* add embedding rpn doc and add show initproposals

* add docstr

* fix backbone lr

* fix typo and change detach_proposal_list to proposal_list

* remove debug assert

* add readme

* add config for random crop when use 300 proposals

* add aug for 300 proposals

* add 300 proposals results and fix docstr

* add 1x results

* fix lint

* fix unitest

* fix docstr of embeddingrpn

* fix according to the comments

* fix get_bbox and a bug of dynamic conv

* support cpu focal loss and fix docstr

* fix docstr

* fix unitest

* fix bug of  init_weight

* fix to device in assign

* fix all commemt

* fix test_config

* remove dim 1 in forward

* fix shape in comment

* fix the case that train_cfg is None

* fix shape of docstr

* fix docstr

* fix typo

* simplify test

* fix docstr

* move train_cfg and test_cfg to model as

* fix unitest

* add link of ckpt and log

* fix 1x results

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

* Fix tag

* Fix DCN tag

* Update tag

* Move train_cfg/test_cfg into model

* fixed fsaf

* fixed missing

* update stat to classify papers

* modify tag of fp16

* update tridentnet model links

* fix log postfix

* 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>

* 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

* 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

* 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

* 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>