* add varifocal loss, vfnet head and config file

* fix nonzero() and register_module bug

* add more configs and README.md

* enlarge image in README.md

* add arxiv link

* add paper arxiv link

* attempt to fix checks error - res2net

* update readme

* update according to comments

* revert res2net.py

* compact the VFNetHead

* adapt for official TTA

* add unit tests and refine vfnet_head

* update url

* update readme

* add minor comments

* update supported models

* remove VFNet.png

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

* Use mmdet.apis

* Add show_dir and show_score_thr args

* pre-commit

* Save each corruption in separate folder

* Save each corruption in separate folder

* speed up and improve stabe paa

* fix yapf

* change default value of covariance_type

* change precisions_init

* Add tied covariance type

* Change default covariance_type

Co-authored-by: d.rybalchenko <d.rybalchenko@visionlabs.ru>
Co-authored-by: rydenisbak <rydenisbak@mail.ru>

* ga ret r50 model url update

* update url

* [enhance]: RoIAlign in mmcv is supported with aligned=False in CPU mode

* [Fix]: RoIPool doesn't have `aligned` attribute

* [enhance]: CPU inference with RoIPool is not supported currently (#3930)

Add supports for giou calculation in BboxOverlaps2D, and re-implements giou_loss using bbox_overlaps (#3936)

* supports for BboxGIoU2D and re-implements giou_loss using bbox_gious

* remove unnecessary

* reformat

* reformat docstring

* reformat

* rename

* supports for giou calculating in BboxOverlaps2D, and re-implements giou_loss using bbox_overlaps

* reformat

* move giou related unit test from test_losses.py to test_iou2d_calculator.py

* reformat

* Avoid division by zero in PAA head when num_pos=0

* explicitly add mode in giou_loss

* edit mmdet.core.export docstring

* update doctest

* fix small bugs

* added `generate_inputs_and_wrap_model` function for pytorch2onnx

* undo debugging changes

* added model.cpu().eval()

* refactored onnx

* fix verify

* move `generate_inputs_and_wrap_model` into mmdet.core.export

* use `generate_inputs_and_wrap_model` in tools/pytorch2onnx.py

* bump to v2.5.0

* update PR

* resolve comments

* clean unnecessary modification

* update bc breaking

* rephrase bc-breaking

* rephrase

* Fix mask rcnn stuck problem when there is no positive rois

* support non pos inference in cascade methods, link CU-49tawu

* print mmcv version in CI

* use mmcv repo to check wrappers

* change cpu build

* upgrade mmcv requirements and change ci back

* use pre-built whl in CI

* support to use pytorch 1.6 in docker

* update mmcv requirement

* update docs

* update tutorials for changing training settings

* update

* Update details of hook

* resolve comments

* reformat

* Update module documentations

* add notes for classes specification

* Convert mask to bool before using it as img's index

* lint

* Rewrite code in more concise way

* Support TTA of ATSS, FCOS, YOLOv3

* Add comment

* Add regression test and test data

* Add fix for empty gt images

* Trigger CI build

* refactor get_subset_by_classes

* reformat and fix docstring

* [refactor]: move get_subset_by_classes to _filter_imgs

* make img_ids consistent

* resolve comments

* simplify logics

* add warning

* add warning

* add warning

Co-authored-by: mmeendez8 <miguelmndez@gmail.com>

* fix rpn transforming bug in two_stage

* Clean background_labels in the dense heads

* clean format

* Reformat

* Fix CI bug

* fix fsaf and the comments

* fix newly added heads

* fix yolact

* complete comments

* update

* fix lint error

* add bbox_pred_split in sabl_head

* fix lint error

* fix yapf

* fix build error

* fix yapf

* add doc of modify loss

* minor fix

* change name

* YOLACT (not the final commit, so please don't review)

* Implementation notes for YOLACT

* Modify yolact_r50.py

* Update YOLACT configs

* Add YOLACT README

* Adjust according to the first round of review

* Handle the corner case when gt_mask is empty

* Add unit tests for YOLACT heads

* Add unit tests for YOLACT forward

* Adjust according to Kai's comments, except for gt_mask filtering

* Change use_OHEM to use_ohem in unit tests

* Update config in YOLACT unit tests

* merge bbox overlap and batch bbox overlap

* fix unit test

* refactor some codes and fix some bugs

* fix isort

* fix ci

* update model link

* fix cfg path

* support batch test

* Make get_seg_masks faster

* fix format

* update readme

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

* re-implement Translate augmentation using mmcv.imtranslate

* add translate abstractmethod for base class

* add PolygonMasks supports toy

* toy commit

* add supports for PolygonMasks

* merge translate.py into auto_augment.py and add unit test for AutoAugment equipped with Translate

* move some variables in call function to self

* fix raising IndexError when getitem from empty index for PolygonMasks

* remove unnecessary interpolation

* add assertion message for fill_val when translating PolygonMasks

* add format

* add comments

* fix handle conflicts

* fix module not registered