GitLab

* test that all configs can be loaded

* Use in_channels correctly in anchor_head and guided_anchor_head

* Fix lint errors. Only tests a subset of configs

* remove local config

* fix yapf

* Remove slower tests

* Remove debug code

* trigger travis

* Added pre-commit hook

* Trigger CI

* update Travis build

* freeze pytorch 1.2

* Install the latest pytorch instead of 1.2

* Revert "Install the latest pytorch instead of 1.2"

This reverts commit d269d2144f9c3b00816b00c31b2b7aa0c5c595f7.

* Delete transforms.py

* Delete extra_aug.py

* Update __init__.py

* Expand docs

* Fix flake8 errors

* Clarify Collect docstring

* revert to the original version

* Doctests for AnchorHead and related code

* Fix flake8 error

* resolve review on transforms.py

* Resolve comments

* resolve commend about foreground classes

* Add reference about bounding box delta encoding

* Albumentations wrapper

* 2 single quote format

* version >= 0.3.2

* Add in_channels kwarg to backbones

* explicit import in HRNet doctest

* Add doctest example for resnet and resnext

* Explicit import in doctests

* Fix missing torch import in doctest

* add foveabox support

* format

* fix

* foveabox correct

* fix mean and std in config

* add foveabox in model zoo

* fix work_dir, typo, fovea_target and config issues

* add necessary comments

* fix yapf issue in C1 check

* fix yapf issue in C1 check

* rename configs

* update model urls and minor fix

* Enable doctests in CI with xdoctest

* use xdoctest in travis file

* Fix doctest warnings

* dont test eggs directory

* Ensure xdoctest is installed before running CI

* Pass device to grid_anchors and valid_flags

* fix yapf formatting

* 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

* Fixed coco_eval bug where seg length check could be wrong (#1376)

* Added check for segm counts field to check if the decode method is present

* Changed classes length check to more general check

* Fixed coco_utils.py to be more robust condition for mask lasbelling

* Added seg length check to ensure two objects exist

* Added type check over len check

* Check for only tuple

* fix dpool

* add _pair in dpool func

* add tta to HTC and Caccade RCNN

* format file with yapf

* fix import error with isort

* Update htc.py

* Update cascade_rcnn.py

* fix bug

* delete some redundant codes

* fix a bug for Modulated Deformable Convolution

* resolve cases for CI test

* resolve cases for CI test

* resolve cases for CI test

* create a new script

* change dir name in config

* update model url

* fix bug when using coco_eval evaluate

* raise TypeError

* add g++ requirement for INSTALL.md.

* fix bugs for cropping masks in RandomCrop.

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

* Update deform_conv_cuda.cpp

* Update deform_pool_cuda.cpp

* fix config

* rm DS_Store

* add 28e

* update model url

* fix bug of ssd

* clean

add RepPoints support

This reverts commit ea9b20af.

* add reppoints head, reppoints detector and the config files.

* add reppoints generator, target and the center-based assigner.

* add readme for RepPoints

* requirements to list in setup to avoid repetitions

* minor refactoring

* 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