* Add RetinetNet parameters in cfg.

* hot fix.

* Add the retinanet head module now.

* Add the function to generate the anchors for RetinaNet.

* Add the SigmoidFocalLoss cuda operator.

* Fix the bug in the extra layers.

* Change the normalizer for SigmoidFocalLoss

* Support multiscale in training.

* Add retinannet  training script.

* Add the inference part of RetinaNet.

* Fix the bug when building the extra layers in retinanet.
Update the matching part in retinanet_loss.

* Add the first version of the inference of RetinaNet.
Need to check it again to see if is there any room for speed
improvement.

* Remove the  retinanet_R-50-FPN_2x.yaml first.

* Optimize the retinanet postprocessing.

* quick fix.

* Add script for training RetinaNet with ResNet101 backbone.

* Move cfg.RETINANET to cfg.MODEL.RETINANET

* Remove the variables which are not used.

* revert boxlist_ops.
Generate Empty BoxLists instead of [] in retinanet_infer

* Remove the not used commented lines.
Add NUM_DETECTIONS_PER_IMAGE

* remove the not used codes.

* Move retinanet related files under Modeling/rpn/retinanet

* Add retinanet_X_101_32x8d_FPN_1x.yaml script.
This model is not fully validated. I only trained it around 5000
iterations and everything is fine.

* set RETINANET.PRE_NMS_TOP_N as 0 in level5 (p7), because previous setting may generate zero detections and could cause
the program break.
This part is used in original Detectron setting.

* Fix the rpn only bug when the training ends.

* Minor improvements

* Comments and add Python-only implementation

* Bugfix and remove commented code

* keep the generalized_rcnn same.
Move the build_retinanet inside build_rpn.

* Add USE_C5 in the MODEL.RETINANET

* Add two configs using P5 to generate P6.

* fix the bug when loading the Caffe2 ImageNet pretrained model.

* Reduce the code depulication of RPN loss and RetinaNet loss.

* Remove the comment which is not used.

* Remove the hard coded number of classes.

* share the foward part of rpn inference.

* fix the bug in rpn inference.

* Remove the conditional part in the inference.

* Bug fix: add the utils file for permute and flatten of the box
prediction layers.

* Update the comment.

* quick fix. Adding import cat.

* quick fix: forget including import.

* Adjust the normalization part according to Detectron's setting.

* Use the bbox reg normalization term.

* Clean the code according to recent review.

* Using CUDA version for training now. And the python version for training
on cpu.

* rename the directory to retinanet.

* Make the train and val datasets are consistent with mask r-cnn setting.

* add comment.

* Adding support to Caffe2 ResNeXt-152-32x8d-FPN-IN5k backbone for Mask R-CNN

* Clean up

* Fixing path_catalogs.py

* Back to old ROIAlign_cpu.cpp file

* Add RPN config files

* Add more RPN models

* [WIP] Keypoints inference on C2 models work

* Training seems to work

Still gives slightly worse results

* e2e training works but gives 3 and 5 mAP less

* Add modification proposed by @ChangErgou

Improves mAP by 1.5 points, to 0.514 and 0.609

* Keypoints reproduce expected results

* Clean coco.py

* Linter + remove unnecessary code

* Merge criteria for empty bboxes in has_valid_annotation

* Remove trailing print

* Add demo support for keypoints

Still need further cleanups and improvements, like adding fields support for the other ops in Keypoints

* More cleanups and misc improvements

* Fixes after rebase

* Add information to the readme

* Fix md formatting

* Registry for RoI Box Predictors

- Add a registry ROI_BOX_PREDICTOR
- Use the registry in roi_box_predictors.py, replacing the local factory
- Minor changes in structures/bounding_box.py: when copying a box with
fields, check if the field exists
- Minor changes in logger.py: make filename a optional argument with
default value of "log.txt"

* Add Argument skip_missing=False

Fixing build-errors on Windows due to invalid types when calling THCCeilDiv. Adding type-cast to (long) to first parameter to fix the errors. (#409)

* make pixel indexes 0-based for bounding box in pascal voc dataset

* replacing all instances of torch.distributed.deprecated with torch.distributed

* replacing all instances of torch.distributed.deprecated with torch.distributed

* add GroupNorm

* add GroupNorm -- sort out yaml files

* use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' and use 'BaseStem'&'Bottleneck' to simply codes

* modification on 'group_norm' and 'conv_with_kaiming_uniform' function

* modification on yaml files in configs/gn_baselines/ and reduce the amount of indentation and code duplication

* use 'kaiming_uniform' to initialize resnet, disable gn after fc layer, and add dilation into ResNetHead

* agnostic-regression for bbox

Since IMS_PER_BATCH is global, it shouldn't be multiplied with the # of GPUs.

* make pixel indexes 0-based for bounding box in pascal voc dataset

* replacing all instances of torch.distributed.deprecated with torch.distributed

* replacing all instances of torch.distributed.deprecated with torch.distributed

* add GroupNorm

* add GroupNorm -- sort out yaml files

* use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' and use 'BaseStem'&'Bottleneck' to simply codes

* modification on 'group_norm' and 'conv_with_kaiming_uniform' function

* modification on yaml files in configs/gn_baselines/ and reduce the amount of indentation and code duplication

* use 'kaiming_uniform' to initialize resnet, disable gn after fc layer, and add dilation into ResNetHead

* Add new section "Projects using maskrcnn-benchmark".

* Update README.md

update the format.

* Update README.md

* Add coco_2017_train and coco_2017_val

* Update README.md

Add the instructions about COCO_2017

* Add new section "Projects using maskrcnn-benchmark".

* Update README.md

update the format.

* Update README.md

fixes #339

This reverts commit 6cbb3d27.

* make pixel indexes 0-based for bounding box in pascal voc dataset

* replacing all instances of torch.distributed.deprecated with torch.distributed

* replacing all instances of torch.distributed.deprecated with torch.distributed

* add GroupNorm

* add GroupNorm -- sort out yaml files

* use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' and use 'BaseStem'&'Bottleneck' to simply codes

* modification on 'group_norm' and 'conv_with_kaiming_uniform' function

* modification on yaml files in configs/gn_baselines/ and reduce the amount of indentation and code duplication

sort keys before reduction

* Update checkpoint.py

if edit "{save_dir}/last_checkpoint" by vim, "\n" will auto append to the end of file. which will raise 

```
FileNotFoundError: [Errno 2] No such file or directory: 'save_dir/model_0060000.pth\n'
```

* Update checkpoint.py

if edit "{save_dir}/last_checkpoint" by vim, "\n" will auto append to the end of file. which will raise
```
FileNotFoundError: [Errno 2] No such file or directory: 'save_dir/model_0060000.pth\n'
```

* Fix indexing error in nms kernel

Here it is indexing a cuda tensor with CPU indices. It used to work, but 
after https://github.com/pytorch/pytorch/commit/006505bb8f9dcf0f38b32518308d071c8a1ccec6 it results in memory corruption.

* Use the device of other tensors

* add force json option

* fix the same issue as #185

* bug fix

* cityscapes config

* update paths catalog

* discard config change

* organize code for more-datasets

* use better representation for coco-style datasets

* rename coco-style config

* remove import

* chmod 644

* make the config more verbose

* update readme

* rename

* chmod