* 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
* update version check
* remove check for onnx
Co-authored-by: maningsheng <maningsheng@sensetime.com>
* 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 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>
* [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
* 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
* supports for onnxruntime custom op `mmcv::MMCVTopPool`
* supports for onnxruntime custom op `mmcv::MMCVCornerPool`, involving TopPool, BottomPool, LeftPool and RightPool
* add unittest for corner_pool
* supports mmcv::CornerPool without memcpy
* add docs for mmcv::CornerPool
* re-add docs for mmcv::CornerPool
* fix output dtype doc
* reformat
* format with pre-commit
* format
* fix lint error, by using google clang-format style for c/c++
* support clipping min_lr in StepLrUpdaterHook
* add docstring for StepLrUpdaterHook
* fix small bugs
* add unit test for StepLrUpdaterHook
* fix linting error
* [Feature] Add PyTorch Profiler to analyze training process
* [Feature] Add PyTorch Profiler to analyze training process
* pring log and fix docstring
* add by_epoch
* modify docstring according to comment
* add torch.cuda.amp to fp16_utils and optimizers
* use with context manager for autocast
* add doc to explain the behavior differences between real amp and ours
* fix docstring
* fix raise error bug in registering multiple names
* fix bug in checking the type of name
* fix lint
* fix unit test for registry
* fix bug in unit test
