S15.2: XFeat exports at a fixed shape and loads under tract

Browse Source

tools/export-xfeat.sh exports the convolutional network alone at 768×1024
grayscale, on the pattern of export-seg-model.sh: thirteen standard
operator types, no dynamic axes, the keypoint decoding left to Rust.
examples/onnx_probe loads it through the ort-over-tract backend the app
ships with nothing unsupported and runs it in ~300 ms on the desktop CPU.

The weights are Apache-2.0, read from the repository's LICENSE, with no
grant on the checkpoint — recorded in models/LICENCE.md before they land,
as FR-MRG-8 asks. The probe stays: the next model will need the same
check.

...

This commit is contained in:

dtourolle

2026-09-19 15:24:10 +02:00

parent 1ded5afbaa

commit e4b6b6c935

6 changed files with 218 additions and 7 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

models/keypoints/xfeat-1024.onnx

LFS

BIN

Binary file not shown.