dgs.models.dataset.keypoint_rcnn

Use keypointrcnn_resnet50_fpn() to predict the key points and bounding boxes of each image.

References

https://pytorch.org/vision/0.17/models/generated/torchvision.models.detection.keypointrcnn_resnet50_fpn.html

Module Classes

KeypointRCNNBackbone(*args, **kwargs)	Metaclass for the torchvision Key Point RCNN backbone model.
KeypointRCNNImageBackbone(*args, **kwargs)	Predicts 17 key-points (like COCO).
KeypointRCNNVideoBackbone(*args, **kwargs)	A Dataset that gets the path to a single Video file and predicts the bounding boxes and key points of the Video.