GitLab

* Code for Paper "Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection"

* fix format

* changed the code according to the Changes requested

* update benchmark

* minor refactoring

* minor fix

* update model_zoo and support models
Co-authored-by: Cao Yuhang <yhcao6@gmail.com>

* First Draft

On branch non-color-images
Changes to be committed:
modified:   mmdet/datasets/pipelines/loading.py

* Add option to load non color images

Add 'color_type' parameter to LoadImageFromFile class
Change __repr__ method accordingly
Since non-color images maybe two dimensional expand image
dimensions if necessary in DefaultFormatBundle and
ImageToTensor classes

Changes to be committed:
    modified:   mmdet/datasets/pipelines/formating.py
    modified:   mmdet/datasets/pipelines/loading.py

* Fix RandomCrop to work with grayscale images

Changes to be committed:
    modified:   mmdet/datasets/pipelines/transforms.py

* Modify retrieving w, h of padded image in anchor heads

This addreses problems with single channel images for which the
shape is  tuple with 2 values

Changes to be committed:
    modified:   mmdet/models/anchor_heads/anchor_head.py
    modified:   mmdet/models/anchor_heads/guided_anchor_head.py
    modified:   mmdet/models/anchor_heads/reppoints_head.py

* Fix issue in refine_bboxes and add doctest

* fix pillow version on travis

* Fixes based on review

* Fix errors in doctest and add comprehensive unit test

* Fix linting error

* add NASFPN

* minor fixes

* fix downsample, add norm to lateral

* update downsample and configs

* remove additional blank line

* update docs

* add benchmark

* minor fix
Co-authored-by: Cao Yuhang <yhcao6@gmail.com>

* init logger before constructing Runner

* use mmdet logger for loading checkpoints

* bug fix for abstract methods

* 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>

* async inference support

* implemented concurrent decorator

* fixes for Python versions < 3.7

* async methods depend on python version

* revert changes in forward method

* async_test -> async_simple_test, debug logging is done via logger.debug

* add async test

* add asynctest to test requirements

* async tests are run in Python 3.7

* check CUDA, add docs

* fix device

* run test only if CUDA is available

* fix linting

* custom operators can run on nondefault stream

* set current stream in kernel launch configuration

* example fixes

* add async/sync interface comparison benchmark

* fix linting

* Remove keep all stage code

* remove keep_all_stage in config

* fix scale factor bug

* reformat

* clean code

* reformat for yapf0.29

* fix conflicts of yapf and flake8

* flake 8 is prior than yapf

* add FreeAnchorRetinanet

* fix std

* refactor code

* add cfg

* fix bug in cfg

* add annotation and clean

* add readme

* fix isort error

* replace clip with torch.clamp

* fix init typo

* refactoring

* clean

* update benchmark

* rename and delete some var

* minor fix

* Fix simple_test for base and fast_rcnn detector

* Add test of detector forward methods

* Revert forward_test change and add docs indicating expected inputs for forward

* fix linter

* Fix GHM loss on CPU

* Fix SSD head on CPU

* 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

* 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

* 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

* 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

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

* 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

* update model zoo

* update model zoo

* update model links

* update HRNet README

* update HRNet README

* remove .DS_Store

* update HRNet results

* update HRNet results and remove .DS_Store

* update FCOS results

* update HRFPN to support FCOS

* remove blank line

* remove blank line

* update Modelzoo

* update models

* update model url

* fix typo

* fix typo

* change name of backbones

* add 20e to cascade w18

* update url

* add flops counter

* minor fix

* add forward_dummy() for most detectors

* add documentation for some tools

* Fix bug of FCOS when image has no positive sample

* somes changes for fcos