tngo
b6c87c45ea
`catalog_hash` hashed the CSV and the view *names*, so replacing `sku_l09.jpg` with a different product's packshot left the hash unchanged and a report could claim the same catalog while every l09 decision in it had moved. It hashes each view's bytes now. `identity_lanes` carried its own `normalize_text` and `bigrams`, near-copies of the ones in `rebuild_catalog` that had already drifted (the lane's table folded ユ to itself, the catalog's did not). The lane imports the catalog's now, so one read scores the same either way. `evidence/image6_v2.json` was byte-identical to `eval/labels/image6.json`; the evidence scripts and the decision document point at the canonical file and the copy is gone. `score_crop`'s docstring now states the contract its callers already depend on: the dict's insertion order is the lane's ranking, and re-sorting by value names a different SKU than the lane chose. Tests: the lane is shared by the classify pool, so a concurrent-ranking test pins that one BFMatcher does not cross crops under eight threads.
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','../../../../eval/labels/image6.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)))
|