Additional Operators for Image Models
Checks if an installation of torchvisionlib was found.
Performs Deformable Convolution v2,
Performs non-maximum suppression (NMS) on the boxes
Performs Position-Sensitive Region of Interest (RoI) Align operator
Read JPEG's directly into torch tensors
Implements additional operators for computer vision models, including operators necessary for image segmentation and object detection deep learning models.
Useful links