tngo
aaed5d388f
Replaces the DINO gallery as the recognition path with the measured design from docs/research/2026-09-28-recognition-architecture/DECISION.md: RootSIFT over a per-SKU reference pyramid, similarity-constrained RANSAC and a hue check, fused with an OCR text lane that vetoes a match whose package text names a different catalog row and answers on its own when geometry finds nothing. - identity_lanes.py: LocalLane, TextLane, DecisionPolicy. The text lane builds each row's signature from the catalog name plus its packshot OCR, so a row with no enrolled image is still answerable. - engine.py: every backend groups scores by canonical SKU, so no view-suffixed id reaches the wire and a name and price always resolve. decide_crop fuses the lanes; score_crop_lanes feeds the live path. Both lanes are built in warm_up (non-fatally) so the first frame is not the slow one, and the text lane shares the engine's OCR lock. - live.py: decides per crop on the lane's own rank order. The lane's order comes from its rank key and its value is only the gate, so re-sorting by value named a different SKU than the lane chose; averaging in an empty observation also diluted a good confidence below the accept line. - identity.py: a `local` score scale whose gate is one absolute line, because the value is already a margin over the runner-up. - app.py, run-demo-server.sh: `--identity local` is the default; the demo server no longer starts on the leaked `stock-lopia` catalog. - eval_live.py: the replay vocabulary accepts `local`, so a recording from the shipped server can be scored. - README.md: documents the three backends and what each is for. Measured on the corrected image6 labels at live resolution: 36/61 in-catalog facings named at 95% precision, 0 of 48 unknowns accepted, 11 labels sourced from the text lane alone. Through the real server: /v1/recognize 90% precision, /v1/stream 100% precision, no view-suffixed ids on either.
47 lines
2.4 KiB
Python
47 lines
2.4 KiB
Python
import pickle, json, sys, numpy as np, collections
|
|
import os; S = sys.argv[1]; L = {f['index']: f['label'] for f in json.load(open(f'{S}/' + os.environ.get('LABELS','image6_v2.json')))['facings']}
|
|
RANK = {
|
|
'inl': lambda e: e['inliers'],
|
|
'inl*col': lambda e: e['inliers'] * (0.25 + e['color']),
|
|
}
|
|
def conf_feats(ranked):
|
|
(k1, e1), (k2, e2) = ranked[0], ranked[1]
|
|
i1, i2 = e1['inliers'], e2['inliers']
|
|
return {
|
|
'inl': i1,
|
|
'margin': i1 - i2,
|
|
'ratio': 1 - i2 / max(i1, 1),
|
|
'inl*ratio': i1 * (1 - i2 / max(i1, 1)),
|
|
'cover': e1['cover'],
|
|
'inl*ratio*qcov': i1 * (1 - i2 / max(i1, 1)) * np.sqrt(e1.get('qcover', 0)),
|
|
'inl*ratio*col': i1 * (1 - i2 / max(i1, 1)) * e1['color'],
|
|
}
|
|
def evaluate(path, rank='inl'):
|
|
r = pickle.load(open(path, 'rb')); E = set(r['enrolled'])
|
|
rows = [x for x in r['rows'] if L[x['index']] != 'exclude']
|
|
n_in = sum(L[x['index']] != 'unknown' for x in rows); n_en = sum(L[x['index']] in E for x in rows)
|
|
recs = []; top1 = 0
|
|
for x in rows:
|
|
t = L[x['index']]
|
|
if not x['ev']: recs.append((t, None, {k: 0 for k in conf_feats([('a', dict(inliers=0,cover=0,color=0)),('b',dict(inliers=0,cover=0,color=0))])})); continue
|
|
ranked = sorted(x['ev'].items(), key=lambda kv: -RANK[rank](kv[1]))
|
|
b = ranked[0][0] if ranked[0][1]['inliers'] > 0 else None
|
|
if t in E and b == t: top1 += 1
|
|
recs.append((t, b, conf_feats(ranked)))
|
|
out = dict(top1=f'{top1}/{n_en}', argmax_e2e=f'{top1}/{n_in}')
|
|
for f in ['inl', 'margin', 'ratio', 'inl*ratio', 'inl*ratio*qcov', 'inl*ratio*col']:
|
|
pts = sorted(((c[f], t == b and b is not None) for t, b, c in recs if b), key=lambda p: -p[0])
|
|
best = {0.9: 0, 0.95: 0, 1.0: 0}; c = a = 0; i = 0
|
|
while i < len(pts):
|
|
j = i
|
|
while j < len(pts) and pts[j][0] == pts[i][0]: c += pts[j][1]; a += 1; j += 1
|
|
for p in best:
|
|
if c / a >= p: best[p] = max(best[p], c)
|
|
i = j
|
|
out[f] = '/'.join(str(best[p]) for p in (1.0, 0.95, 0.9))
|
|
return out
|
|
if __name__ == '__main__':
|
|
print('feature cells = correct accepted at precision 100%/95%/90% (enrolled in-catalog n=42, all in-catalog n=61, unknown n=48)')
|
|
for p in sys.argv[2:]:
|
|
for rk in ['inl', 'inl*col']:
|
|
print(p.split('/')[-1].replace('.pkl',''), rk, json.dumps(evaluate(f'{S}/{p}', rk)))
|