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.
29 lines
1.8 KiB
Python
29 lines
1.8 KiB
Python
import sys,os,json,pickle,numpy as np,cv2,time
|
|
sys.path.insert(0,'code'); sys.path.insert(0,os.path.dirname(__file__))
|
|
from ocr import VisionOcr
|
|
from diag import crops
|
|
S=os.path.dirname(__file__)
|
|
L=json.load(open(f'{S}/../../../../eval/labels/image6.json'))
|
|
# distinguishing tokens per SKU (any hit counts); includes siblings for near-unknowns
|
|
KEY={'sku_l01':['エッグケア','卵を使って'],'sku_l02':['アマニ'],'sku_l03':['からし','Spicy'],'sku_l04':['めんたい'],
|
|
'sku_l05':['ゼロ','ノンコレ'],'sku_l06':['フィッテ','内臓脂肪'],'sku_l07':['ラッキー'],'sku_l08':['PERI','ペリ'],
|
|
'sku_l09':['コクうま','65'],'sku_l10':['ピュアセレクト','マヨネーズ'],'sku_l11':['ハーフ','1/2'],'kewpie450':['KEWPIE','マヨネーズ']}
|
|
o=VisionOcr(languages=['ja-JP','en-US']); out={}
|
|
for res in ['full','live']:
|
|
rows=[]
|
|
for fc,c in crops('add/image6.jpg',L,res=='live'):
|
|
if fc['label']=='exclude' or c.size==0 or min(c.shape[:2])<8: continue
|
|
for up in [1,2]:
|
|
cc=cv2.resize(c,None,fx=up,fy=up,interpolation=cv2.INTER_CUBIC) if up>1 else c
|
|
t=time.perf_counter(); r=o.read(cc); ms=(time.perf_counter()-t)*1000
|
|
txt=' '.join(l.text for l in r.lines)
|
|
rows.append(dict(index=fc['index'],truth=fc['label'],up=up,text=txt,ms=ms))
|
|
out[res]=rows
|
|
pickle.dump(out,open(f'{S}/ocr.pkl','wb'))
|
|
for res,rows in out.items():
|
|
for up in [1,2]:
|
|
rr=[r for r in rows if r['up']==up]; tr=[r for r in rr if r['truth'] in KEY]
|
|
hit=sum(any(k in r['text'] for k in KEY[r['truth']]) for r in tr)
|
|
print(res,'up',up,f'in-catalog key-token hit {hit}/{len(tr)}','median ms',round(np.median([r['ms'] for r in rr]),1))
|
|
for r in out['live']:
|
|
if r['up']==2 and r['truth']!='unknown': print(r['index'],r['truth'],'|',r['text'][:80])
|