* 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

* Support faster rcnn

* Fix Lint

* Add docstr

* Fix docstr

* Update docstr

* Update code

* Update docstr

* Add check for ann_ids not unique

* Update

* Rename variable and add comments

* add onnx unit test

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* reset retinanet and yolo head and neck unit test

* rename the function

* add annotation

* update function structure

* remove _get_bboxes_single() unit test case

* add comments

* fix onnx deploy bug in anchor_head.py

* replace os.open to mmcv.load

[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>

* bbox coder support batch infer

* Add unit test

* get img_shape as tensor in single_stage

* Fix max_shape

* Update docs and unittest

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

* Refactor unittest

* Fix unittest

* Fix unittest

* Replace util with mmcv testing

* Try to reduce the unit test memory

* use isinstance method to get loading pipeline

* Fix isinstance error

* Add unit test

* Fix lint

* Fix lint

Co-authored-by: hhaAndroid <1286304229@qq.com>

* clean deprecated fp16 api

* clean fp16 import in core

* add a abvious import

* add a assert for CLASSES in XMLDataset

* change to get

* add voc tiny dataset

* add tiny voc

* add voc init test

* change to smalle iamge

* add xmlsubclass check

* add smaller image

* add comment for assert

* Support get plt frame data

* Add grayscale image unittest and fix comment

* Clean empty line and fix comment

* Add unit test and fix comment

* Update inference and add unit test

* Fix lint

* Fix abnormal resource usage

* Update unit test

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

* 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

* fix: mask resize

* test: mask resize

* chore: fix lint

* 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>

* New Add ResultEvaluate

* Update ResultVisualizer

* Delete debug code

* Add Loading related pipeline

* 1.Move retrieve_loading_pipeline to dataset.util
2.Support display GT mask
3.Support display GT mask and det mask for visualize fn

* Use gt_mask.to_ndarray()

* Refactor analyze_results.py

* Fix docs str

* Logger is silent and add progressBar

* Fix lint

* Fix docs str and other comment

* Fix docs str

* Fix docs str

* Fix docs str and add unit test for mask2ndarray

* Move train_cfg/test_cfg into model

* fixed fsaf

* fixed missing

* FPN deprecated warning

* FPN deprecated warning

* Replace imshow_det_bboxes visualization backend

* Add bbox_vis unit tests

* Encapsulate color_val_matplotlib function

* Add fun input parameters

* Deprecate block

* Add mask display in image

* Putting the text inner left corner the bbox

* Add a filling color for text regions.

* Update color docs

* Fix color docs

* Update color docs and Fix default param

* 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

* 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>

* 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

* 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 detr config for higher performance

* fix unit tests

* supports for DETR transformer

* unit test with small data to avoid out of memory in CI

* use batch size 1 for unit test to avoid out of memory

* move transformer into utils folder and use more small data for unit test

* reformat docstring

* add more detailed docstring

* reforamt

* reformat and add build_transformer (#3866)

* Supports for DETR position embedding (#3850)

* supports for DETR position embedding

* reformat docstring

* reformat

* move transformer_head folder into utils

* remove unnecessary comments

* reformat

* reformat

* reformat docstring

* reformat

* add optional for default parameters

* add comments for unit test

* avoid inplace in MultiheadAttention and add optional add_residual for FFN

* Supports for DETR inference (#3941)

* fix forward in FFN

* supports detr inference mode with batchsize 1

* add docstring for DETR in detr.py

* reformat and add doctest for TransformerHead

* reformat, and move the mask construction from simple_test in detr.py to the forward process of transformer_head

* rename detr_r50_1x_coco as detr_r50_8x4_1x_coco in config

* reformat

* mask input_img_shape in img_meta as a general modification of base_detector forward_test

* reformat

* Supports for DETR hungarian matcher. (#3929)

* Add doc of modify loss (#3777)

* add doc of modify loss

* minor fix

* change name

* improve the function of simple_test_bboxes (#3853)

* update

* fix lint error

* add bbox_pred_split in sabl_head

* fix lint error

* fix yapf

* fix build error

* fix yapf

* Clean background_labels in the dense heads (#3221)

* 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

* fix rpn transforming bug in two stage networks (#3754)

* fix rpn transforming bug in two_stage

* [Refactor] refactor get_subset_by_classes in dataloader for training with empty-GT images (#3695)

* 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 nonzero in NMS for PyTorch 1.6.0 (#3867)

* Support TTA of ATSS, FCOS, YOLOv3 (#3844)

* Support TTA of ATSS, FCOS, YOLOv3

* Add comment

* [Docs] Fix typo in docs/tutorials/new_dataset.md (#3876)

* [Docs] Remove duplicate content in docs/config.md (#3875)

* [Enhance]: Convert mask to bool before using it as img's index for robustness and speedup (#3870)

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

* lint

* Rewrite code in more concise way

* Fix typo in bbox_flip (#3886)

* fix the API change bug of PAA (#3883)

* fix cv2 import error of ligGL.so.1 (#3891)

* [enhance]: Improve documentation of modules and dataset customization (#3821)

* update tutorials for changing training settings

* update

* Update details of hook

* resolve comments

* reformat

* Update module documentations

* add notes for classes specification

* support to use pytorch 1.6 in docker (#3905)

* support to use pytorch 1.6 in docker

* update mmcv requirement

* update docs

* Add missing notes in data customization (#3906)

* [Fix]: fix mask rcnn training stuck problem when there is no positive rois (#3713)

* 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

* Bump to v2.5.0 (#3879)

* bump to v2.5.0

* update PR

* resolve comments

* clean unnecessary modification

* update bc breaking

* rephrase bc-breaking

* rephrase

* Added `generate_inputs_and_wrap_model` function for pytorch2onnx (#3857)

* 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

* typo (#3917)

* Edit mmdet.core.export docstring (#3912)

* edit mmdet.core.export docstring

* update doctest

* fix small bugs

* supports for HungarianMatchAssigner, add bbox_cxcywh_to_xyxy and bbox_xyxy_to_cxcywh for bbox transform

* format box-wise related giou calculating as a function and implement it in iou2d_calculater.py

* 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

* fix sabl validating bug in cascade_rcnn (#3913)

* 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

* [Fix]: Avoid division by zero in PAA head when num_pos=0 (#3938)

* explicitly add mode in giou_loss

* 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

* Add supports for giou calculation in BboxOverlaps2D, and add iou_calculator in hungarian_assigner

* rename hungarian_match_assigner as hungarian_assigner

* fix init

* reformat docstring

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

* fix cpu (#3948)

* add mode for iou_calculator and make giou cost as a default case

* make mode as a param in iou_calculator

* reformat docsting

* make iou_mode outside of iou_calculator

Co-authored-by: Cao Yuhang <yhcao6@gmail.com>
Co-authored-by: yuzhj <31239926+yuzhj@users.noreply.github.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
Co-authored-by: mmeendez8 <miguelmndez@gmail.com>
Co-authored-by: Yosuke Shinya <42844407+shinya7y@users.noreply.github.com>
Co-authored-by: LabMemNo003 <LabMemNo003@gmail.com>
Co-authored-by: Ye Liu <yeliudev@outlook.com>
Co-authored-by: aboettcher <aboettcher@users.noreply.github.com>
Co-authored-by: Ryan Li <xlide@connect.ust.hk>
Co-authored-by: Jiangmiao Pang <pangjiangmiao@gmail.com>

* Re-implements RandomCrop to support different crop_type (#4093)

* re-implements RandomCrop to support different crop_type

* add assertion for relative related crop_type

* reformat, and add image shape assertion for unit test

* reformat

* Supports for DETR training mode in process. (#3963)

* add input_img_shape in img_meta, and supports training mode toy

* toy commit

* toy commit

* re-organize and support for detr training mode

* add unit test for detr training, testing, and transformer_head

* add more unit test for transformer

* reformat

* remove unnecessary

* use small transformer model for unit test

* reformat docstring

* reformat

* reformat

* Supports DETR e150 config (#4197)

* rename e300 config as e150 config

* reformat

* add comments on override option in Resize

* add comments on override option in Resize

* position embeddingto positional encoding

* fix unit tests

* fix registry name bug

* rename file

* remove unnecessary

Co-authored-by: ZwwWayne <wayne.zw@outlook.com>
Co-authored-by: Cao Yuhang <yhcao6@gmail.com>
Co-authored-by: yuzhj <31239926+yuzhj@users.noreply.github.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
Co-authored-by: mmeendez8 <miguelmndez@gmail.com>
Co-authored-by: Yosuke Shinya <42844407+shinya7y@users.noreply.github.com>
Co-authored-by: LabMemNo003 <LabMemNo003@gmail.com>
Co-authored-by: Ye Liu <yeliudev@outlook.com>
Co-authored-by: aboettcher <aboettcher@users.noreply.github.com>
Co-authored-by: Ryan Li <xlide@connect.ust.hk>
Co-authored-by: Jiangmiao Pang <pangjiangmiao@gmail.com>

* [Feature] Add best ckp hook

* update docstring

* Fixed evaluate

* make key_indicator default None

* add test, and OrderDict

* add test fot best checkpoint hook

* delete comments

* add more info

* fixed eval metric

* remove key_indicator

* update doc

* fixed test.py/eval_metric.py

* fixed dist

* compatible with mmcv

* more test

* revert voc0712

* add stem_channels opt

* add ResNeSt

* fixed config

* fixed cascade config

* add precise BN

* add precise bn in test

* format precise bn

* update precise bn interval

* fixed eval config bug

* fixed precise interval

* change to return_loss=False

* add naive syncbn

* add naive syncbn

* rmo precise bn

* add range ms

* change to MMSyncBN

* add naive

* fixed loader

* reset test

* fixed faster config bug

* add no norm decay

* add baseline no norm decay

* set fronzen_stages=-1

* move import

* restore to official setting

* set to MMSyncBN

* update s101 pretrain

* update docs

* fixed config

* add backbone+head

* change fpn init

* add s101

* add s101

* revert fpn init

* add modelzoo, docstring, test

* fixed test

* fixed test

* add missing models

* update docstring

* add comment

* fixed markdownlint

* fix pytorch 1.7 imcompatibility issues

* remove useless files

* add faster rcnn C5

* add trained faster rcnn C5 model url

* fix typos

* update based on 1-st comments

* update unittest for ChannelMapper

* small changes of ChannelMapper's docstring

* small changes of ChannelMapper's docstring

* 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>

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

* 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>

* 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

* implements augmentation which only transform images (e.g. Color,Sharpness) in process

* Add augs which only transform image (e.g. Sharpness, Equalize, Color) in process.

* remove test_augonlyimg.py

* re-implement color,brightness,equalize,contrast using mmcv

* rename aug_only_img as img_augment

* remove aug_only_img related files

* merge img_augment.py into auto_augment.py

* add Rotate augmentation init

* add coco_dummy data for unit test of augmentations

* add coco_dummy data for unit test of augmentations

* add Rotate augmentation

* remove duplicated warpAffine declaration.

* remove unnecessary coco_dummy folder

* re-implements rotate augmentation upon mmcv.imrotate

* fix uint test

* reformat

* add supports for PolygonMasks

* handle __init__ conflicts

* unchange

* pull from master and merge rotate.py into auto_augment.py

* add unit test for autoaugment equipped with rotate

* move random_negative_prob to self and reformat assertion message

* add Shear augmentation.

* remove duplicated warpAffine declaration.

* fix shear bboxes

* re-implements Shear augmentation using mmcv.imshear

* fix the name of some variables

* reformat

* add shear abstractmethod for BaseInstanceMasks

* supports for PolygonMasks

* add docstring

* add more unit test

* reformat assertion message

* remove unnecessary comma in function

* refactor

* remove unnecessary

* remove unnecessary copy

* mergt shear.py into auto_augment.py

* add unit test for autoaugment equipped with shear