GitLab

* add tensor2imgs in misc

* rename

* fixed import

* raise error

* update actiion

* remove 1.3 cuda

* reorder

* add no torch

* fixed version

* make py3.8 on pt1.5

* make py3.8 on pt1.5

* remove torch 1.3

* disable py3.8

* pip

* merge master with cuda compile fix

* add cpu roi align

* fixed test

* fixed no torch

* add CUDA_ARGS

* use one line

* gencode=61

* seperate jobs

* update lint

* use parametrize test

* formart and rename

* unit test for all

* 1. use macro USE_PARROTS control header include
2. add clang-format google style in pre-commit

* use MMCV_ macros

* fix bug of building ConvModule with HSigmoid using inplace=True and add corresponding unittest

* fix linting

* add ext ops, support parrots

* fix lint

* fix lint

* update op from mmdetection

* support non-pytorch env

* fix import bug

* test not import mmcv.op

* rename mmcv.op to mmcv.ops

* fix compile warning

* 1. fix syncbn warning in pytorch 1.5
2. support only cpu compile
3. add point_sample from mmdet

* fix text bug

* update docstrings

* fix line endings

* minor updates

* remove non_local from ops

* bug fix for nonlocal2d

* rename ops_ext to _ext and _ext to _flow_warp_ext

* update the doc

* try clang-format github action

* fix github action

* add ops to api.rst

* fix cpp format

* fix clang format issues

* remove .clang-format
Co-authored-by: Kai Chen <chenkaidev@gmail.com>

* Add utils to calculate model complexity info

* remove _InstanceNorm in unittest

* add docstring and increase unittest coverage

* fix deconv_flops_counter_hook to accept different data shape

* test when model is not a common instance

* put flops_counter.py and weight_init.py into mmcv/cnn/utils folder

* fix import name

* reformat some docstrings

* update the scripts with latest one and remove redundant codes

* directly represent a model without string and eval()

* reformat code

* use mmcv without installing pytorch

* add new line

* revise utils.init by try-except-else block

* add new line to utils.init

* del whitespace in new line

* add flake8 ignore to utils.__init__

* feat: support for os.environ port for slurm training

* fix: port data type

* feat: add flawed unittest

* feat: add flawed unittest

* docs: add comments

* fix: unittest

* fix: unittest

* add hswish and hsigmoid

* fix linting

* fix linting

* delete useless staticmethod in cnn/bricks/hsigmoid.py

* forward(x) ==> forward(seld, x)

* add unittests for hsigmoid and hswish

* use torch.equal instead of numpy.equal

* fix: fix custom_keys whenweight_decay is not specified

* docs: small fix

* feat: add type check

* refactor: move if outside for

* add non_local module

* rewrite non local module comments

* perfect docstring and adjust init function

* not to init norm layer

* Correct initialize when there is a norm

* set normal method for both embedded_gaussian and dot_product

* feat: add custom_group to DefaultOptimConstrutor

* refactor: move custom_groups validate to _validate_cfg

* docs: add doc to explain custom_groups

* feat: add unittest for non_exist_key

* refactor: one param per group

* fix: small fix

* fix: name

* docs: docstring

* refactor: change to mult for only lr and wd custom

* docs: docstring

* docs: more explaination

* feat: sort custom key

* docs: add docstring

* refactor: use reverse arg of sorted

* docs: fix comment

* docs: fix comment

* refactor: small modi

* refactor: small modi

* refactor: small modi

* feat: modify parallel to module wrapper

* fix: unittest

* fix: add registry file

* feat: add module wrapper unittest

* add backend arg

* add test

* update doc, add test

* update test

* update doc

* load_checkpoint support normal dict checkpoints

* comments

* fix bug in using inner iter when by_epcoh==True

* set default for log config

* fix bug: remove optim in val, use iter in log when by_epoch is False

* added pillow backend in loading

* reformat

* remove auto fill for RGBA

* change according to comments

* change according to comments

* reformat

* feat: add CosineRestartLrUpdaterHook

* style: rename period to periods

* fix: bug in period 0

* feat: rename eta_min to min_lr and add min_lr_ratio

* docs: fix docstring of restart lr updater

* refactor: use annealing_cos

* docs: add docstring to annealing_cos

* feat: cosine restart lr update hook

* refactor: modify code order for unittest

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

* Update conv_module.py

* No bracket for simple class
Signed-off-by: lizz <lizz@sensetime.com>

* Remove more unused things
Signed-off-by: lizz <lizz@sensetime.com>

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

* feat: add IterBasedRunner

* fix: unittest

* feat: more unittest

* fix: expose dataloader len

* minor updates of BaseRunner

* refactor: remove CosineRestartLrUpdaterHook

* style: add docstring

* refactor: update IterTextLoggerHook: fstring and exp_name

* fix: epoch_runner unittest

* refactor: remove IterBasedTextLogger

* fix: old IterTextLoggerHook issue

* refactor: remove __len__ of IterLoader

* feat: add IterBasedRunner to init

* feat: add __len__ to IterLoader

* fix some docstrings

* refactor: use is_parallel_module

* fix: import issue

* fix: runner unittest missing logger

* fix checkpoints

* feat: add by_epoch default value to IterBaseRunner regitering loggger_hook

* refactor: remove setting by_epoch in log_config

* minor refactoring

* docs: add docstring

* fix: remove unused doc

* update the log info for saving checkpoints
Co-authored-by: Kai Chen <chenkaidev@gmail.com>

* Add syntax check in .py config

* rename validate