* [doc]: add doc for pytorch2onnx

* [doc]: remove blank lines

* resolve format of doc

* refact doc for pytorch2onnx

* add space

* add to index.rst

* FPN deprecated warning

* FPN deprecated warning

* Add the documentation of batch inference and test

* Add the documentation of options cfg and eval cfg

* Modify the document description

* Add doc description spacer

* Update doc description

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

* undo

* fix #3950, avoid zero or too small value for new_beta

* make eps as global var

* 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 #4181, invalid link in readme for maskrcnn cityscapes

* undo

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

* updating performance

* fix detr config for higher performance

* fix unit tests

* fix bug in distributed sampler

* add comments to explain the modification

* revise according to comments

* Add markdown lint in pre-commit hook

* add markdown lint

* FPN deprecated warning

* FPN deprecated warning

* update Readme of SABL

* update download link

* fix bug: PAFPN has no attribute extra_convs_on_inputs

* add on_lateral

* fix lint

* fix lint error

* support return indices when using nms

* support return indices when using nms

* support return indices when using nms

* support return indices when using nms

* Update gfl_head.py

There is a error in pytorch1.6 version when call reduce_mean in this head: input tensor is "int" format, can not call div_ direct. so, change it to float format.

* Update gfl_head.py

* Update cross_entropy_loss.py

Fix device type bug for weight copy.

* Update cross_entropy_loss.py

Fix bug: device type error when copying weight value.

* Update cross_entropy_loss.py

Fix bug: device type error when copying weight value.

* Update cross_entropy_loss.py

Fix bug: device type error when copying weight value.

* bump to v2.7.0

* update dates

* update version requirements

* rephrase

* resolve comments

* Add DETR readme.md

* update model zoo

* fix typo

* 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>

* [docs] Add loss convention

* add example

* fixed backticks

* reduce code

* fixed lint

* [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

* Edit faq to add 30 series installation problem

* Update as per comment

* add options to override used configs in inference.py

* fix typo

* update parrots ci

* fix mmcv install

* update ci

* Update build.yml

* Modify to export to ONNX

* Modify to support new_tensor, new_full when exporting to onnx

* Replace grid_sample with resize for exporting to onnx

* Add verify of mask result

* Verify all outputs between pytorch and onnx

* Avoid runtime split error for mask-rcnn

* Remove unnecessary change in bbox2roi

* 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

Added instructions related to the docker version to ensure that user is not running into issues mentioned here https://github.com/NVIDIA/nvidia-docker/issues/1165

* add model stastics

* add modelzoo Statistics

* fix some title in READMD

* chmod

* fix parrots compatibility

* add comments

* masks from (n,h,w) to [(h,w),...,(h,w)]

* Update transforms.py

* Update transforms.py

* forward compatible

* upgrade yapf

* minon clean

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

* update

* clip border

* clip border

* clip

* update

* update

* update

* update