GitLab

* 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

* +super().before_run()

* flip reset_flag

* read in rb mode then decode

* Update config.py

* Update .pre-commit-config.yaml

* Update config.py

* Update config.py
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>

* add license

* fix lint

* fix some discription

* fix some discriptions and dirty marks

* fix format

* revise some words

* Update README_zh-CN.md

* Update README_zh-CN.md
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>

* fix load_ckpt

* revised according to comments

* revise according to comments

* fix typo

* Remove iter number in logging during val/test time

* Fix typo

* modified EvalHook for eval mode to print the correct iter number

* [Docs] Update weight initialization in cnn.md

* Update cnn.md

* [Docs] Update weight initialization in cnn.md

* [Docs] Update weight initialization in cnn.md

* [Docs] Update weight initialization in cnn.md

* [Docs] Update weight initialization in cnn.md

* [Docs] Update weight initialization in cnn.md

* modify docs according to comments

* modify docs for weight init according to the comment

* change init_weight() to init_weights()

* modify according to comment

* Assign different priority to default hooks, and add custom hook register in base runner.

* Add custom hook register in example train file

* Add unittest of custom hook

* Code format

* fix basemodule

* fix typo

* fix unitest

* fix basemodule

* add commnet

* add pixel group ops

* reformatting

* formatting&rm auto

* Add citation

* Add contour expand

* c++ linting

* Add unit tests with Tensor

* rm model.pth

* rename

* c++ linting

* c++ linting

* Rename variables

* add StepMomentumUpdaterHook

* add unit test

* fix typos

* refactor step updater

* replace stage with exp

* fix linting error

* use all() operation

* [Fix] lr add triangular

* [Fix] lr_triangular

* lr add docstring

* lr add docstring

* add unittest of triangular lr update

* [Fix] Fix DCN fp16

* add comment

* Add test util for checking stand-alone scripts
Signed-off-by: lizz <lizz@sensetime.com>

* Restrict to python scripts
Signed-off-by: lizz <lizz@sensetime.com>

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

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

* Allow no capture
Signed-off-by: lizz <lizz@sensetime.com>

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

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

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

* Update hello.py

* Update test_testing.py

* Update test_testing.py

* support custom op `mmcv::cummax` for onnxruntime in mmcv

* fix clang-format lint error

* support mmcv::cummin, reformat codes

* fix merge from master

* add docs for mmcv::cummax and mmcv::cummin

* format doc

* add assertion for torch version, when exporting `cummax` to onnx

* add more comments for torch version

* handle exporting to onnx in `soft_nms`

* commit for test_onnx

* remove `is_in_onnx_export` in softnms

* add more comments

* fix c++ lint error

* add known issues doc for `cummax`

* fix known issues doc