facebookresearch/detectron2 v0.2 on GitHub

Support constructing objects with either configs or explicit arguments. As an example, the entire Mask R-CNN can be built without using configs
Rename TransformGen to Augmentation and keep TransformGen as an alias. Design the interface of Augmentation so that it can access arbitrary custom data types. See augmentation tutorial for details.
Improve speed of COCOEvaluator by about 3x
Support LVIS v1 dataset
Support GIoU loss in RPN and R-CNN
Support auto-scaling of batch size and learning rate in DefaultTrainer. See cfg.SOLVER.REFERENCE_WORLD_SIZE

Pre-built Linux binaries are provided for the following environment:

CUDA	torch 1.5	torch 1.4
10.2	install `python -m pip install detectron2==0.2 -f \ https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.5/index.html`
10.1	install `python -m pip install detectron2==0.2 -f \ https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.5/index.html`	install `python -m pip install detectron2==0.2 -f \ https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.4/index.html`
10.0		install `python -m pip install detectron2==0.2 -f \ https://dl.fbaipublicfiles.com/detectron2/wheels/cu100/torch1.4/index.html`
9.2	install `python -m pip install detectron2==0.2 -f \ https://dl.fbaipublicfiles.com/detectron2/wheels/cu92/torch1.5/index.html`	install `python -m pip install detectron2==0.2 -f \ https://dl.fbaipublicfiles.com/detectron2/wheels/cu92/torch1.4/index.html`
cpu	install `python -m pip install detectron2==0.2 -f \ https://dl.fbaipublicfiles.com/detectron2/wheels/cpu/torch1.5/index.html`	install `python -m pip install detectron2==0.2 -f \ https://dl.fbaipublicfiles.com/detectron2/wheels/cpu/torch1.4/index.html`