Switch Frigate detector from CPU/TFLite to ONNX with YOLO-NAS-s

Uses YOLO-NAS-s model exported at 320x320 resolution, stored on NFS
at /media/frigate/models/yolo_nas_s.onnx. Significantly better
detection accuracy than the default SSD MobileNet V1.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Erich Blume 2026-02-14 21:20:12 -08:00
commit a153843d7e

View file

@ -39,8 +39,17 @@ data:
track: [person, car, dog, cat, bird]
detectors:
cpu:
type: cpu
onnx:
type: onnx
model:
model_type: yolonas
width: 320
height: 320
input_tensor: nchw
input_pixel_format: bgr
path: /media/frigate/models/yolo_nas_s.onnx
labelmap_path: /labelmap/coco-80.txt
record:
enabled: true