GitLab

* Fix the permission denied error on windows.

* Format code.

* Using a cleaner way.

* Update config.py

use os.unlink instead of unlink

* change  unlink to remove

* add notes for new implementation

* Fix typo
Co-authored-by: WRH <12756472+wangruohui@users.noreply.github.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>

* EvalHook uses case-insensitive key indicator matching and configurable test functions

* * fix docstring

* * move test_fn import into __init__
* configurable greater/less keys

* * update unittest
* update DistEvalHook

* fix comments and remove debug code

* support single greater/less key

* add resize or rescale to multiple

* add imresize_to_multiple function in mmcv.image

* fix docstring

* use to_2tuple

* empty tensor inference backward continity

* update

* add 3d

* add to_ntuple

* add unit test

* add modulated dcn, better dcn plugin

* clangformat

* update documentation

* avoid bc-breaking

* fix function name

* fix typo

* fix import

* add import warning

* remove wapper

* remove unitest

* add dep warning

* add dep warning

I need this in a subclass, but I dont want copy the whole `log()` function

* minor changes

* change to modulist

* change to Sequential

* replace dropout with attn_drop and proj_drop in MultiheadAttention

* add operation_name for attn

* add drop path and move all ffn args to ffncfgs

* fix typo

* fix a bug when use default value of ffn_cfgs

* fix ffns

* add deprecate warning

* fix deprecate warning

* change to pop kwargs

* support register FFN of transformer

* support batch first

* fix batch first wapper

* fix forward wapper

* fix typo

* fix lint

* add unitest for transformer

* fix unitest

* fix equal

* use allclose

* fix comments

* fix comments

* change configdict to dict

* move drop to a file

* add comments for drop path

* add noqa 501

* move bnc wapper to MultiheadAttention

* move bnc wapper to MultiheadAttention

* use dep warning

* resolve comments

* add unitest:

* rename residual to identity

* revert runner

* msda residual to identity

* rename inp_identity to identity

* fix name

* fix transformer

* remove key in msda

* remove assert for key
Co-authored-by: HIT-cwh <2892770585@qq.com>
Co-authored-by: bkhuang <congee524@gmail.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>

* fix cast nn.Module bug

* fix misleading doc

* add resume function

* del useless; fix typo

* change meta structure; set resume default

* Fix export to onnx for PointRend

* Fix codestyle

* Fix codestyle

* Fix type in docstring

* Minor fix

* Fix export with custom ops

* Fix codestyle

* Add tests for bilinear_grid_sample function

* Remove redundant operation and rename variables

* Fix bug in bilinear_grid_sample and update test

* Fix getting batch size

* skip torch==1.3.1

* remove unused import

* fix lint

* support export with batch

* fix dynamic clip

* skip test for torch<1.5.0

* Add docstrings and comments

* Minor fix

* Recover clipping code

* Fix clamping in pytorch 1.7.0

* Fix bilinear_grid_sampler

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

* add runner doc

* revised according to comments and remove non existing links

* revise according to comments

* Add dvclive logger hook

* Move docstring to class

* docstring updates

* [WIP] Updata initialization documents

* [Fix] Fix the docstring for initializers

Signed-off-by: lizz <lizz@sensetime.com>

* [Fix] Support names of base classes matching in init_cfg

* revise bool to len

* Add score_threshold and max_num to NMS

* Fix codestyle

* Fix codestyle

* Fix inds in nms

* Update nms docstring

* Move score_threshold and max_num arguments

* Fix args order in docstring

* fix lint of c++ file

* Remove torch.onnx.is_in_onnx_export() and add max_num to batched_nms for separate classes.

* Rewrote max_num handling in NMSop.symbolic

* Added processing max_output_boxes_per_class when exporting to TensorRT

* Added score_threshold and max_num for NMS in test_onnx.py and test_tensorrt.py

* Remove _is_value(max_num)

* fix ci errors with torch==1.3.1

* Update test_batched_nms in test_nms.py

* Added tests for preprocess_onnx

* Moved 'test_tensorrt_preprocess.py' and 'preprocess', updated 'remove_tmp_file'.

* Update mmcv/tensorrt/__init__.py

* Fix segfault torch==1.3.1 (remove onnx.checker.check_model)

* Returned 'onnx.checker.check_model' with torch version check

* Changed torch version from 1.3.1 to 1.4.0

*...

* add instancenorm plugin

* resolve comments

* fix lint

* fix typo

* support cuda version `BorderAlign` module

* fix symbolic

* merge

* fix cpp lint error

* add unit test

* add comments for code references

* reformat doc

* fix lint error

* fix conflict

* Fix typos
Signed-off-by: lizz <lizz@sensetime.com>

* Add deprecation warning
Signed-off-by: lizz <lizz@sensetime.com>

* add cummax/cummin tensorrt plugin

* fix isort

* fix with clang-format

* fix with clang-format again

* add document

* [Feature] Add truncated normal weight init

* [Feature] Add truncated normal weight init

* [Feature] Add truncated normal weight init

* update docstring

* delete modelA.pth

* modify according to comment

* use kstest to check truncated normal

* delete modelA.pth

* fix test.txt

* fix fp16 bug on DCNv2

* support fp16 on DCN/DCNv2 when pytorch >= '1.6.0'

* add comment

* Modified the comments

* Unified the usages of '.to()' and '.type_as()'

* add neptune.ai logger hook

* add docstring

* move docstring

* update docstr

* update before_run

* fix generalized attention fp16

* fix building without gpu error

* add comment

* Cast tensor at initialization