* update model zoo

* update model zoo

* update model links

* update HRNet README

* update HRNet README

* remove .DS_Store

* update HRNet results

* update HRNet results and remove .DS_Store

* update FCOS results

* update HRFPN to support FCOS

* remove blank line

* remove blank line

* update Modelzoo

* update models

* update model url

* fix typo

* fix typo

* change name of backbones

* add 20e to cascade w18

* update url

* update readme

* add different datasets on model zoo

* add major components for training double head

double head only with two losses and no attention

remove double_head detector for now, merge upchannel to double_head bbox head

change the stype using yapl

remove uncessary comment#

to pass check

to pass v2

to pass v3

line too long and style again

reuse bottlenet

* refactoring

* bug fix

* bug fix for weight initialization

* add reg roi scale factor and modify loss weights

* rescale the roi after mapping to fpn levels

* added cityscapes

* updated configs

* removed wip configs

* Add initial dataset instructions

* Add cityscapes readme

* Add explanation for lr scaling

* Ensure pep8 conformity

* Add CityscapesDataset to the registry

* add benchmark

* rename config, modify README.md

* fix typo

* fix typo in config

* modify INSTALL.md

Update information how to arrange cityscapes data.

* Add cityscapes class names

* add fp16 support

* fpn donot need bn normalize

* refactor wrapped bn

* fix bug of retinanet

* add fp16 ssd300 voc, cascade r50, cascade mask r50

* fix bug in cascade rcnn testing

* add support to fix bn training

* add fix bn cfg

* delete fixbn cfg, mv fixbn fp16 to a new branch

* fix cascade mask fp16 bug in test

* fix bug in cascade mask rcnn fp16 test

* add more fp16 cfgs

* add fp16 fast-r50 and faster-dconv-r50

* add fp16 test, minor fix

* clean code

* fix config work_dir name

* add patch func, refactor code

* fix format

* clean code

* move convert rois to single_level_extractor

* fix bug for cascade mask, the seg mask is ndarray

* refactor code, add two decorator force_fp32 and auto_fp16

* add fp16_enable attribute

* add more comment, fix format and test assertion

* fix pep8 format error

* format commont and api

* rename distribute to distributed, fix dict copy

* rename function name

* move function, add comment

* remove unused parameter

* mv decorators into decorators.py, hook related functions to hook

* add auto_fp16 to forward of semantic head

* add auto_fp16 to all heads and fpn

* add docstrings and minor bug fix

* simple refactoring

* bug fix for patching forward method

* roi extractor in fp32 mode

* fix flake8 error

* fix ci error

* add fp16 support to ga head

* remove parallel test assert

* minor fix

* add comment in build_optimizer

* fix typo in comment

* fix typo enable --> enabling

* udpate README

* add grid benchmark

* minor update to readme

* add benchmarks

* add ghm x101-64x4d

* fix a model url

* add training and inference speed

* Grid R-CNN

* add grid_rcnn_res50fpn2x config

* add assertion that grid_head should exist

* fix bugs and remove SharedFCBBoxHeadGrid

* remove the property with_grid

* format fixes for grad_head and add config dir

* move random_jitter to grid_head and some refactoring

* simplify the calculation of num_edges

* refactoring

* refactoring

* rename config files and add x101 config

* bug fix for inference

* remove random_jitter_single

* add readme of grid rcnn

* add bibtex of grid rcnn plus

* update work_dir

* add ms-rcnn

* fix config

* fix bug in test

* fix bug in test, det_labels should plus 1

* add area ratio

* speed up area ratio calculation

* delete caffe style config

* refactor code, bbox and segm eval using different score

* fix bug in distevalhook

* update README and config

* update x101-64x4d

* refactor code

* update upstream

* format

* update r50 and r101 2x performance

* update ms-rcnn-x101-64x4d-2x performance

* move simple_mask_test, add docstring and comment

* delete TODO in mask iou target

* add detail comment to mask iou target

* modify comment of mask iou target

* move mask iou target to mask iou head

* merge mask_iou_target and get_target

* add MSELoss for MaskIoUHead and rename mask_iou to fc_mask_iou

* refactoring

* fix bug in test

* fix bug when cropping mask inside proposal

* update readme

* update bibtex

* remove space in bibtex

* Add support of the wider face dataset

* Update readme

* Prevent ignoring boxes in test mode

* Rename wider to wider_face

* Rename configs for wider face

* refactoring for losses

* update configs for guided anchoring

* add all imported losses to __all__

* allow weight=None for binary_cross_entropy

* use losses in mmdetection for FCOSHead

* bug fix for weight_reduce_loss

* add eps to iou_loss and handle weight=None

* unify loss api in FCOSHead

* fix avg_factor

* update configs and related code

* remove debug info

* fix style issues

* fix unnecessary changes

* move generalized_attention.py from ops/dcn to models/plugins

* change the arguments name of generalized attention, add related description and update resnet backbone

* revert the change of weight_init.py

* format touched files by yapf

* change default data_root

* update code for passing flake8 test

* delete unnecessary __init__.py

* Change the argument order of resnext.__init__()

* remove constant_init

* simplifying the init of generalized_attention module

* remove unused import

* format the code

* change the name of config folder, add more configs, add README.md

* rename num_head to num_heads

* minor formatting

* Fix bugs in the configs of Libra R-CNN

* return configs to 2000 props

* return configs to 1000 props

* add pytorch 1.1.0 SyncBN support

* change BatchNorm2d to _BatchNorm and call freeze after train

* add freeze back to init function

* fixed indentation typo in adding freeze

* convert SyncBN to BN when eval is called

* add gcb and configs

* fixed line too long

* fixed space and newline

* ignore too long line in config files

* two space before inline comment

* refactor var name

* fixed line too long

* changed SyncBN to backbone only and add non-Sync BN configs

* reformat config to adapt master branch

* reformat change method->type

* remoe some configs

* clean up readme.md

* add benchmark

* fix typo in README

* change sbn to syncbn

* change work dir

* refactor gcb

* fixed line too long

* Code formatting

* finish ghm in newest verion with AP 37.0

* add ghm config file

* reformat for PEP8

* reformat for flake8

* add documents for GHM and tensorize the params

* improve the docs

* add readme and update configs

* Code for components of Libra R-CNN

* Configs and README for Libra R-CNN

* update bfp

* Update Model ZOO

* add comments in non-local

* fix shape

* update bfp

* update according to ck's comments

* update des

* update des

* fix loss

* fix according to ck's comments

* fix activation in non-local

* fix conv_mask in non-local

* fix conv_mask in non-local

* Remove outdated model urls

* refactoring for bfp

* change in_channels from list[int] to int

* refactoring for nonlocal

* udpate weight init of nonlocal

* minor fix

* update new model urls

* add fcos_r50_bn, fcos_r50_2x_no_ms benchmark

* split table by ms-training

* adjust table

* add r101 2x without ms train performance

* add two stage w/o neck and w/ upperneck

* add rpn r50 c4

* update c4 configs

* fix

* config update

* update config

* minor update

* mask rcnn support c4 train and test

* lr fix

* cascade support upper_neck

* add cascade c4 config

* update config

* update

* update res_layer to new interface

* refactoring

* c4 configs update

* refactoring

* update rpn_c4 config

* rename upper_neck as shared_head

* update

* update configs

* update

* update c4 configs

* update according to commits

* update

* add ga rpn

* test bug fix

* test bug fix with loc_filter_thr is large

* update configs

* update configs

* add ga_retinanet

* ga test bug fix

* update configs

* update

* init masked conv

* update

* update masked conv

* update

* support no ga_sampler

* update

* update

* test with masked_conv

* update comment

* fix flake errors

* fix flake 8 errors

* refactor bounded iou loss

* refactor ga_retina_head

* update configs

* refactor masked conv

* fix flake8 error

* refactor guided_anchor_head and ga_rpn_head

* update configs

* use_sigmoid_cls -> cls_sigmoid_loss; use_focal_loss -> cls_focal_loss

* refactoring

* cls_sigmoid_loss -> use_sigmoid_cls

* fix flake8 error

* add some docs

* rename normalize to norm_cfg

* update configs

* add readme

* update ga_faster config

* update readme

* update readme

* rename configs as r50_caffe

* merge master

* refactor guided anchor target

* update readme

* update approx mas iou assigner

* refactor guided anchor target

* update docstring

* refactor ga heads

* fix flake8 error

* update readme

* update model url

* update comments

* refactor get anchors

* update docstring

* not use_loc_filter during training

* add R-101 results

* update to support build loss api

* fix flake8 error

* update readme with x-101 performances

* update readme

* add a link in project readme

* refactor code about ga shape inside flags

* update

* update

* add x101 config files

* add ga_rpn r101 config

* update some comments

* add comments

* add comments

* update comments

* fix flake8 error

* support HRNet

* add zip

* remove zip files

* remove zip datasets in config

* modify format and shorten lines

* fix line to long

* support conv_cfg and update conv layer

* revise the backbone network and neck

* update format and pretrained mode

* fix flake8 error

* update modules following review suggestions

* revert some changes for adapting to pretrained models

* update hrnet and hrfpn

* remove unused import

* remove unused import

* finish testing

* change pretrained model link to open-mmlab

* fix docstring and convert models

* update README and model links

* modify configs and README

* support loss evaluator

* update model urls

* format hrnet.py

* format hrfpn.py

* add 20e for cascade config

* Fix license in setup.py

* Add code for loss evaluator

* Configs support loss evaluator

* Fix a little bug

* Fix flake8

* return revised bbox to reg

* return revised bbox to reg

* revision according to comments

* fix flake8

* add training from scratch with GN

* rename and format

* change resnet initialization

* update scratch results

* Reformat use yapf 0.27.0

* Add yapf style file

* add fcos

* use P5 instead of C5

* add relu before extra convs in FPN

* add singleclass_nms, use caffe2 lr

* fix log interval

* use caffe2init and relu in extra layers

* fix scale layer, use p5 instead of c5

* fix focs target

* refactor code

* delete useless file

* clean

* refactor code

* change num_classes to cls_out_channels

* fix bug of in get_bboxes

* fix bug in test

* add r101 2x cfg

* ms use value mode, add x101-64x4d cfg

* add more comment and rename some variable

* rename centers to points, modify doc string of distance2bbox

* add fcos detector, replace frozen with requires_grad

* add README.md

* add r101-1x performance, rename cfg, add detector FCOS

* update fcos r50 2x performance, remove fpn caffe2 initialize

* fix flake8 error

* rename cfg

* fix grammar error of some comments

* minor fix comment

* change work_dir to be consistent with config name

* add FCOS support in README

* use_sigmoid_cls -> cls_sigmoid_loss; use_focal_loss -> cls_focal_loss

* fix flake8 error

* cls_sigmoid_loss - > use_sigmoid_cls

* rename c4 configs

* update model zoo with c4 benchmark

* reorder c4 benchmarks

* update model zoo

* rename normalize to norm_cfg

* update configs

* Update resnet.py

* use different configs for proposal train/test

* update configs for dcn

* update inf speed

* update inf speed in dcn, gn, htc

* update comparision

* keep backward compatibility

* add support for weight standardization

* add ws support for htc heads

* add a config file for 20-23-24e lr schedule

* update readme of weight standardization

* add HybridTaskCascade

* add configs for other backbones

* add keep_ratio argument for segmap transform

* add readme for HTC

* fix linting errors

* split assign and sampling as in Cascade R-CNN

* remove unused imports

* add a large model

* update htc