* [doc]: add doc for pytorch2onnx

* [doc]: remove blank lines

* resolve format of doc

* refact doc for pytorch2onnx

* add space

* add to index.rst

* [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

* 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 rpn upgrade scripts for v2.5.0 compatibility

* rephrase docs

* 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

* 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

* fix rpn transforming bug in two_stage

* fix bc break of mmdet.core.fp16, refactor import of wrap_fp16_model

* changed warning method

* added docstring for Depr_Fp16OptimizerHook

* docformatter

* fix docstring

* changed names from depr to deprecated

* Change all fp16 operation to using MMCV

* fix isort

* yapf and docformatter

* Revert "yapf and docformatter"

This reverts commit dede22f5339e04002ccad4e7c4c7bbb083b2e6dc.

* yapf

* Add replace_ImageToTensor for batch inference

* move replace_ImageToTensor to mmdet.datasets.utils

* fix typo in unit tests

Co-authored-by: Kai Chen <chenkaidev@gmail.com>

* update some models

* some fix

* support cascade

* add htc

* sup more models

* sup point rend

* clean comment

* minor fix

* clean

* fix unittest

* update doc

* fix image demo and robustness test

* fix webcame

* Add custom_imports

* Add tutorial

* import import_modules_from_strings later to be compatible with previous mmcv versions

* Add config and config filename to runner meta

* Add absolute path of config file

* change from realpath to abspath

* Use copy.deepcopy

* Use config instead of config_dict.

* add eval metric

* update

* support to evaluate concatenated dataset

* rm pdb

* update model zoo

* resolve comments

* Add assert during initialization

* more flexible usage

* add unittests

* change order of unittests

* Docs (new_datasets): update docs about concat dataset eval

* Docs (new_datasets): update docs about concat dataset eval

* Resolve comments

* Resolve comments

* Add eval-option flag for testing

* Update description

* Add BC

* Update docs

* merge with cfg.evaluate

* add more info

* add more keys to pop

* add docs

* Update pytorch2onnx.py which using new logic to convert pytorch to ONNX

* use standard API to check whether in ONNX convert process

* only compare the score value while verifying results between ONNX and pytorch

* move import onnx before import torch, or something weird will happen

* use real images for input

* modifying the way of calling nms

* modify docstring for bbox2result, and remove unnecessary part for onnx exporting

* modify the 'Convert to ONNX' part in docs

* replace or to | in docstring

* update according to the latest mmcv

* add normalize part

* raise error while using low version mmcv

* minor update

* minor update

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>

* update setup.py

* update collect_env accordingly

* rm VERSION and hardcode version.py

* Use get_git_hash in mmcv

* fix bug of version_file

* use function to parse version

* use __version__

* only print first 7 of git hash

* resolve comments

* Fix torch install issue in action

* clean op

* clean

* update build.yml

* fix setup

* change ci mmcv version

* change ci mmcv version

* add install pre-build mmcv instructions

* update mmcv url, move some unnit tests to mmcv

* update ci mmcv

* test

* test

* test

* fix unit test

* fix unit test

* fix onnx script

* update mmcv url

* fix typo

* fix some doc

* Bump version

* resolve comments

* Fix version bug

Co-authored-by: ZwwWayne <wayne.zw@outlook.com>

* update docstring formats

* fix :func:

* minor update

* Add support for DetectoRS.

* Fix Travis CI build failure and remove loading rfp_pretrained for test

* Revise the code according to the PR reviews:

* remove unnecessary `,`

* add docstring to ASPP and ConvAWS2d

* make args of ASPP configurable

* simplify the code of ConvAWS2d

* import nn and functional for SAConv2d

* rewrite rfp_conv with build_conv_layer and constant_init

* rename rfp_inp with rfp_inplanes

* reformat code to pass Travis CI build

* Revise codes according to the PR reviews:

* Create new backbone DetectoRS_ResNe(X)t to incorporate RFP and SAC.

* Initialize modules with mmcv.cnn.

* Revise the codes of RFP.

* Revise codes according to the PR comments:

* Add docstrings to Bottleneck in mmdet/models/backbones/detectors_resnet.py.

* Add docstrings to _load_from_state_dict in mmdet/ops/conv_ws.py.

* Initialize the switch of SAC with mmcv.

* minior refactor and docstring

* update doc

* update README

* move init into init_weights()

* update model zoo

* add gfl

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>

* migrate flops counter to mmcv

* remove useless unit tests

* update the doc

* Add RegNet, docs/refactor TBD

* Support RegNet

* Add RegNets

* Modify docs and refactor code

* fix pre-train bug

* Performance ready

* Use public model weights

* Performance & settings done

* Fix unittest bug

* Try another way of test config

* Add unittest and refactor

* Reformat

* Finish refactor regnet

* merge tests

* fix conflicts

* Fix resnext CI bug

* rename parameter

* Add ref link & clean _delete_

* tweaks of doc

* try resnext doctest

* add expansion in block

* remove doctest of resnext

* update inf speed

* update some models

* update benchmark config and model

* add no aug config

* merge log model table with performance table

* add detectron2 url

* compute pure inference time instead

* fix batch size

* fix batch size bug

* use img metas

* Delete file

* reformat

* fix yapl

* fix comments

* add python path in scripts

* Make python path work

* Shorter path

* Add docs

* Change dist scripts

* Change slurm example

* Fix validate default bug

* Change docs accordingly