ANSFR: configurable slow-attribute refresh interval

New API SetANSRFAttributeInterval(Handle, frames) / UpdateAttributeInterval
(1..60, default 5) controls how often the slow attributes (age/gender +
emotions) refresh per camera; head pose and recognition are unaffected.
GetANSRFModelInfo now reports "attribute_interval". The adaptive logic's
stable-scene branch previously capped at a hardcoded 10 - it now doubles
the configured interval instead (default behaviour 10/5/2 unchanged).

Motivation: the v1.4 ViT age-gender model is heavier per attribute frame
than the old OpenVINO IR. Interval sweep on RTX 3070 (classroom.mp4,
~3.1 faces/frame) vs the v1.1 baseline at 16.0 ms / 62 fps:
  interval  5 (default): 19.9 ms / 50 fps  (+3.9 ms)
  interval 10:           17.1 ms / 58 fps  (+1.1 ms)
  interval 20:           16.5 ms / 61 fps  (parity)
Recommendation: default on 8 GB GPUs; interval 10 on small-VRAM machines.

ANSFR-UnitTest: --bench old|new [interval] runs the sweep.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-27 01:57:54 +10:00
co-authored by Claude Fable 5
parent 89b2efe182
commit f34817c620
4 changed files with 63 additions and 8 deletions
+13
View File
@@ -98,6 +98,13 @@ namespace ANSCENTER
bool UpdateFaceQueue(int queueSize, int faceThresholdSize, bool enableFaceQueue);
bool GetFaceQueue(int& queueSize, int& faceThresholdSize, bool& enableFaceQueue);
// How often the slow attributes (age/gender + emotions) refresh:
// every N frames per camera (1 = every frame). Head pose still runs
// every frame. The adaptive logic doubles N on stable scenes and
// halves it (min 2) when faces appear/disappear. Default 5.
bool UpdateAttributeInterval(int frames);
int GetAttributeInterval() const { return _attributeInterval; }
// Recognizer model switching (0 = AdaFace [default], 1 = ArcFace).
// Before LoadEngine: just records the preference. After LoadEngine:
// re-initializes the recognizer, regenerates every stored embedding
@@ -391,6 +398,12 @@ extern "C" ANSFR_API int GetANSRFRecognizerModel(ANSCENTER::ANSFacialRe
// JSON describing the loaded models, e.g.
// {"recognizer_model":"adaface","agegender_backend":"onnx","emotion_backend":"onnx",...}
extern "C" ANSFR_API int GetANSRFModelInfo(ANSCENTER::ANSFacialRecognition** Handle, LStrHandle modelInfo);
// Slow-attribute (age/gender + emotions) refresh interval in frames per
// camera (1 = every frame, default 5; clamped to [1, 60]). Larger values
// cut the attribute-model GPU cost proportionally at the price of slower
// attribute updates — useful on smaller GPUs with the heavier v1.4 ONNX
// age-gender model. Returns 1 on success, -1 on invalid arguments.
extern "C" ANSFR_API int SetANSRFAttributeInterval(ANSCENTER::ANSFacialRecognition** Handle, int frames);