Skip to content

v0.1.1: LightGlue-ONNX-MP

Compare
Choose a tag to compare
@fabio-sim fabio-sim released this 11 Jul 15:36
· 47 commits to main since this release
75ec0e8

LightGlue-ONNX Mixed Precision Models

This release provides mixed-precision-exported ONNX models of the DISK, SuperPoint (feature extractors), and LightGlue (keypoint matcher) models (*_mp.onnx). Both standalone models and end-to-end pipelines (*_end2end_mp.onnx) are provided. Mixed precision is generally faster than full precision but is only supported on CUDA. Please refer to EVALUATION.md for detailed speed comparisons.