dtourolle 4ed29b9d81 Add the int8 detectors for the Hexagon, calibrated on real photographs ...

tools/quantise-models.sh writes the QDQ form QNN's HTP backend takes
whole: opset 17, per-channel int8 weights, uint8 activations, ranges
from running the f32 graph over photographs fed exactly as the app
feeds them. The calibration is strided, four images at a time, because
every ONNX Runtime calibrator holds each image's whole set of
activations until it folds them — a gigabyte an image on the 10g
detector, and an OOM kill with no message when folded once at the end.

Release-time, never on the device (docs/inference.md §5): it needs
real photographs and a person reading the recall measurement that
gates whether each file is offered.

2026-09-19 16:02:37 +02:00

913 KiBLFS

Raw History

View Raw