product-recognition-demo/recognization/data/external-eval/kewpie/eval_result.json
kiyo9w 11826cc43c feat(eval): report the external benchmark per SKU
A set total hides which products the lane can and cannot name. Every SKU in
these sets has images from two independent source domains, so a SKU that scores
the same on both is not one lucky photograph.

The breakdown is what makes the two interesting results visible: l01, l02, l03,
l07 and l09 are 2/2 correct on both their domains, l07 with no enrolled image
at all, while l11 abstains on both and l04 abstains on all four of its images.
2026-09-29 03:37:04 +09:00

150 lines
No EOL
2.7 KiB
JSON

{
"dataset": "kewpie",
"catalog": "stock-lopia-clean",
"note": "External proxy images, not Tier 2. Scored through the shipped LocalLaneAdapter + DecisionPolicy.",
"rows": [
{
"file": "sku_l01_1.jpg",
"truth": "sku_l01",
"best": "sku_l01",
"confidence": 13.1618,
"status": "success",
"source": "local",
"verdict": "correct"
},
{
"file": "sku_l01_2.jpg",
"truth": "sku_l01",
"best": "sku_l01",
"confidence": 20.986,
"status": "success",
"source": "local",
"verdict": "correct"
},
{
"file": "sku_l02_1.jpg",
"truth": "sku_l02",
"best": "sku_l02",
"confidence": 10.4288,
"status": "success",
"source": "text",
"verdict": "correct"
},
{
"file": "sku_l02_2.jpg",
"truth": "sku_l02",
"best": "sku_l02",
"confidence": 7.542,
"status": "success",
"source": "local",
"verdict": "correct"
},
{
"file": "sku_l03_1.jpg",
"truth": "sku_l03",
"best": "sku_l03",
"confidence": 14.3581,
"status": "success",
"source": "local",
"verdict": "correct"
},
{
"file": "sku_l03_2.jpg",
"truth": "sku_l03",
"best": "sku_l03",
"confidence": 48.9767,
"status": "success",
"source": "local",
"verdict": "correct"
},
{
"file": "sku_l05_1.jpg",
"truth": "sku_l05",
"best": null,
"confidence": 0.0,
"status": "unknown",
"source": null,
"verdict": "abstain"
},
{
"file": "sku_l05_2.jpg",
"truth": "sku_l05",
"best": "sku_l05",
"confidence": -3.9674,
"status": "success",
"source": "text",
"verdict": "correct"
},
{
"file": "sku_l06_1.jpg",
"truth": "sku_l06",
"verdict": "leaked",
"leaked_into": "sku_l06",
"note": "enrolled in the catalog; scoring it would be training accuracy"
},
{
"file": "sku_l06_2.jpg",
"truth": "sku_l06",
"best": "sku_l06",
"confidence": 294.8985,
"status": "success",
"source": "local",
"verdict": "correct"
},
{
"file": "sku_l11_1.jpg",
"truth": "sku_l11",
"best": null,
"confidence": -29.9175,
"status": "unknown",
"source": null,
"verdict": "abstain"
},
{
"file": "sku_l11_2.jpg",
"truth": "sku_l11",
"best": null,
"confidence": 14.1552,
"status": "ambiguous",
"source": null,
"verdict": "abstain"
}
],
"scored": 11,
"leaked": 1,
"by_sku": {
"sku_l01": {
"correct": 2,
"abstain": 0,
"wrong": 0
},
"sku_l02": {
"correct": 2,
"abstain": 0,
"wrong": 0
},
"sku_l03": {
"correct": 2,
"abstain": 0,
"wrong": 0
},
"sku_l05": {
"correct": 1,
"abstain": 1,
"wrong": 0
},
"sku_l06": {
"correct": 1,
"abstain": 0,
"wrong": 0
},
"sku_l11": {
"correct": 0,
"abstain": 2,
"wrong": 0
}
},
"correct": 8,
"abstain": 3,
"wrong": 0
}