GitLab

Fix retinanet r50 2x model error

* fixed a bug which causes merged_proposals are only from a certain scale of proposals in aug_test_rpn

* add a comment and modify _img_metas to aug_img_metas

* Update Libra R-CNN Benchmark

* fix bug in balanced_l1_loss

* Set LOCAL_RANK in script.
Fix multiple checkpoint download bug
Signed-off-by: innerlee <363664470@qq.com>

* beautify
Signed-off-by: innerlee <363664470@qq.com>

* 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 losses.py

* Update losses.py

Signed-off-by: innerlee <363664470@qq.com>

* fix mask conv import error

* fix masked_conv cuda runtime error when mask is all zero

Signed-off-by: innerlee <363664470@qq.com>

* 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

* code formatting for guided_anchor_head.py

* bug fix for using multi_apply

* 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

update init_detector() & inference_detector() parameter

* 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 detectron2pytorch

* update

* 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

* update the high-level inference api

* save classes in meta data and use it for visualization