GitLab

* Split seg trans

* Modify cfg

* fix typo

* Allow for images to contain zero true detections

* Allow for empty assignment in PointAssigner

* Allow ApproxMaxIouAssigner to return an empty result

* Fix CascadeRNN forward when entire batch has no truth

* Correctly assign boxes to background when there is no truth

* Fix assignment tests

* Make flatten robust

* Fix bbox loss with empty pred/truth

* Fix logic error in BBoxHead.loss

* Add tests for empty truth cases

* tests faster rcnn empty forward

* Skip roipool forward tests if torchvision is not installed

* Add tests for bbox/anchor heads

* Consolidate test_forward and test_forward2

* Fix assign_results.labels = None when gt_labels is given; Add test for this case

* Fix OHEM Sampler with zero truth

* remove xdev

* resolve 3 reviews

* Fix flake8

* refactoring

* fix yaml format

* add filter flag

* minor fix

* delete redundant code in load anno

* fix flake8 errors

* quick fix for empty truth with masks

* fix yapf error

* fix mask padding for empty masks
Co-authored-by: Cao Yuhang <yhcao6@gmail.com>
Co-authored-by: Kai Chen <chenkaidev@gmail.com>

* reformat for yapf0.29

* fix conflicts of yapf and flake8

* flake 8 is prior than yapf

* Fix issues on no ignore boxes specified

* add check during loading

* change back

* change transform.py back

* fix box_filed bug & reformat

* use append rather than extend

* Update GETTING_STARTED.md

Found out that this method is required. The torch.nn.Module doesn't contain this method thus you need to implement it

* update docstring 

see https://github.com/open-mmlab/mmdetection/issues/1582

* correct for flake8

* flake8: trailing space has removed

Allows to use not only 0.5 probability.

* Fix bug: index out of range when num_extra < len(indice)

* Fix bug: index out of range when num_extra < len(indice)

* formatter code

* Still work if no img_prefix specified

* Update default param to be empty string

* Add seg transform to Expand and MinIoUCrop

* fix bug of repr

* Delete transforms.py

* Delete extra_aug.py

* Update __init__.py

* Expand docs

* Fix flake8 errors

* Clarify Collect docstring

* revert to the original version

* Albumentations wrapper

* 2 single quote format

* version >= 0.3.2

* Fix #1223

#1223  is caused by extra > len(indice), so I add a loop to properly pad the indice list. I also changed the list concatenation from ```+=``` to ```.extend```.

* Update sampler.py

style

* add g++ requirement for INSTALL.md.

* fix bugs for cropping masks in RandomCrop.

* simplify the code to fix bugs for cropping masks in RandomCrop.

* fix bug of ssd

* clean

* define data pipelines

* update two config files

* minor fix for config files

* allow img_scale to be optional and update config

* add some docstrings

* add extra aug to transform

* bug fix for mask resizing

* fix cropping

* add faster rcnn example

* fix imports

* fix robustness testing

* add img_norm_cfg to img_meta

* fix the inference api with the new data pipeline

* fix proposal loading

* delete args of DefaultFormatBundle

* add more configs

* update configs

* bug fix

* add a brief doc

* update gt_labels in RandomCrop

* fix key error for new apis

* bug fix for masks of crowd bboxes

* add argument data_root

* minor fix

* update new hrnet configs

* update docs

* rename MultiscaleFlipAug to MultiScaleFlipAug

* add __repr__ for all transforms

* move DATA_PIPELINE.md to docs/

* fix image url

* Added vertical flipping in bbox_flip

* Fixed linting errors

* Fixed linting errors

* Added a blank line in docstrings

* Fixed linting errors.

* Add robust detection benchmark

* Update readmes

* Changed readmes for pull request

* Ensure pep8 conformity

* fixed formatting

* Fix yapf errors

* minor formatting

* fix imports order

* fix the imports in __init__.py

* update contribution guide

* add isort config

* use isort to sort imports

* add isort to travis

* format the codebase with yapf

* add yapf to travis

* added cityscapes

* updated configs

* removed wip configs

* Add initial dataset instructions

* Add cityscapes readme

* Add explanation for lr scaling

* Ensure pep8 conformity

* Add CityscapesDataset to the registry

* add benchmark

* rename config, modify README.md

* fix typo

* fix typo in config

* modify INSTALL.md

Update information how to arrange cityscapes data.

* Add cityscapes class names

* Require an operation(Save or Show the results) when testing

* using parentheses

* Warning when skip image

* added parameter skip_img_without_anno for dataset

* print filename when warning

* Added Registry use for validation datasets (distributed)

* Allowing for default_args for build_dataset

* Using build_dataset instead of build_from_cfg

* Fixing build-errors on Windows (add some compile args, which are default on Linux)

* Fixing build-errors on Windows

* minor formatting

* Fixing errors on windows

1.Adding 'cxx' key for extra_compile_args
2.Adding type-cast to long for first parameter of THCCeilDiv facebookresearch/maskrcnn-benchmark#409
3.Ignoring resource setting on windows

* update the order of import statements

* use registry to manage datasets

* bug fix for concat dataset

* update documentation to fit the new api

* Fix an import error for `get_world_size` and `get_rank`

* Only import torch.distributed when needed

torch.distributed is only used in DistributedGroupSampler

* use `get_dist_info` to obtain world size and rank

`get_dist_info` from `mmcv.runner.utils` handles the problem of `distributed_c10d` doesn't exist.

* Add support of the wider face dataset

* Update readme

* Prevent ignoring boxes in test mode

* Rename wider to wider_face

* Rename configs for wider face

* Reformat use yapf 0.27.0

* Add yapf style file