ruv
486392bb68
docs: update ADR-079 with validated hardware, ruvector optimizations, baseline
...
- Status: Proposed → Accepted
- Add O6-O10 optimizations (subcarrier selection, attention, Stoer-Wagner
min-cut, multi-SPSA, Mac M4 Pro training via Tailscale)
- Add validated hardware table (Mac camera, MediaPipe, M4 Pro GPU, Tailscale)
- Add baseline benchmark results (PCK@20: 35.3%)
- Update implementation plan with completion status
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-06 14:38:40 -04:00
ruv
e3522ddcda
feat: camera ground-truth training pipeline (ADR-079, #362 )
...
Add 4 scripts for camera-supervised WiFlow pose training:
- collect-ground-truth.py: synchronized webcam + CSI capture via
MediaPipe PoseLandmarker (17 COCO keypoints at 30fps)
- align-ground-truth.js: time-align camera keypoints with CSI windows
using binary search, confidence-weighted averaging
- train-wiflow-supervised.js: 3-phase supervised training (contrastive
pretrain → supervised keypoint regression → bone-constrained
refinement) with curriculum learning and CSI augmentation
- eval-wiflow.js: PCK@10/20/50, MPJPE, per-joint breakdown, baseline
proxy mode for benchmarking
Baseline benchmark (proxy poses, no camera supervision):
PCK@10: 11.8% | PCK@20: 35.3% | PCK@50: 94.1% | MPJPE: 0.067
Camera pipeline validated over Tailscale to Mac Mini M4 Pro
(1920x1080, 14/17 keypoints visible, MediaPipe confidence 0.94-1.0).
Target after camera-supervised training: PCK@20 > 50%
Closes #362
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-04-06 14:07:25 -04:00
