GitLab

* add onnx support to roi_align and roi_pool

* add test on roi_align and roi_pool

* fix conflict with master

* update README.md for torch 1.7 installation

* add cuda 11.0
Co-authored-by: Kai Chen <chenkaidev@gmail.com>

* add CLAHE

* add CLAHE

* restore

* Add docstring

* modify docstring

* modify CLAHE to clahe

* fix syntax error

* simplify assert

* simplify assert

* add assert test

* fix unittest bug

* fix syntax bug

* fix assert bug

* add lut_transform

* restore

* fix test bug

* add test

* Fix syntax bug

* Delete test id

* modfiy docstrinng

* simplify assert

* [Feature] Add hook msg for ckpt_hook

* [Feature] Add hook msg for ckpt_hook

* add test

* fix issues when converting deformable convolution to onnx

* keep  and  for interface consistency
Co-authored-by: maningsheng <maningsheng@sensetime.com>

* Update lr_updater.py

since epoch/iteration in  runner starts with 0, we shouldn't leave the latter iteration to former (12th epoch for example, with first period equal to 12) period.

* Update lr_updater.py

* Update test_hooks.py

* Fix logger iter

* Fix logger iter

* add dynamic scale

* add type check of loss scale

* fix lint

* minor fix

* support pytorch 1.7 and update the CI

* fix CI

* fix onnxruntime version in macos

* Add 'config' keyword in meta for pavi logger

* Use config file

* SKIP bbox test without CUDA

* use full filepath for creating latest.pth

* Refactor tags for consistency

* Fix missing runner

* Fix missing runner

* Fix missing runner

* Fix missing runner

* Fix momentum runner hook inner iter

* Fix tests

* pre-commit run

* add unittest for onnx convert

* build onnx and onnxruntime in CI

* skip onnx op unit test while using CUDA

* fix offset==0 case in NMS

* remove tmp file used in test

* delete tmp file before assert so that we can remove the tmp file anyway

* Skip opencv requirement if it's already installed in the env

* pre-commit

* Check opencv conda version

* Check opencv conda version

* import_modules_from_strings when loading cfg from file

* add unittest to tell whether the feature is enabled as expected

* minor

* set an environment variable instead of writing a file

* use 'shutil' instead of 'os.system'

"please use MMDistributedDataParallelinstead." -> "please use MMDistributedDataParallel instead."

* Add Sync buffer in CheckpointHook

* add reduce_params in fp16_utils.py

* change default value of sync_buffer to False

* Add world size check

* reset sync_buffer to false

* fix world_size

* Move dist functions into dist_utils.py

* fix small bugs

* Deprecation compatibility

* Change according to comments

* fix wrappers when using parrots

* linting

* refactor according to review

* fix bug in resuming optim-dict

* add raise error when meeting unexceptable type

* add raise error when meeting unexceptable type

* add version check in wrappers

* fix assersion

* use digital version for version comparison

* fix unit tests

* reformat

* fall back to compare the first two version

* fix unittest

* fix unittest

* fix unit test

* clean unnecessary change

* register deconv in CONV_LAYERS

* use ConvTranspose2d implemented in MMCV

* remove repetitive register_module

* update

* add unittest for deconv

* Support to specify LR of DCN's conv_offset

* Resolve comments & add unit test

* Resolve formats

* Fix CI for DCN

* Mock DCN when cpu only

* Use mock for cpu testing

* Fix docstring and support ModulatedDCN

* set offset_lr_mult as dcn's arguments, link CU-49u01p

* fix lr bug

* fall back to set LR in constructor

* resolve comments

* add torchvision roi_align with aligned=True

* fix for lint test

* fix for lint test2

* format use yapf

* Add build_runner

* Parametrize test_runner

* Add imports to runner __init__

* Refactor max_iters and max_epochs from run to init

* Add assertion error messages

* Add test_builder

* Make change retro-compatible

* Raise ValueError if max_epochs and max_iters