forked from vnguyen/product-recognition-demo

History

kiyo9w 6a45fb990d fix(catalog): enroll the current l06 package, closing F-12 The enrolled sku_l06.jpg showed the superseded 内臓脂肪ケア wrapper. The shelf and the current retail package both read 内臓脂肪を減らすキューピーフィッテ 210g, so the reference image was of a design the store no longer sells - the catalog was pointing at the wrong package. F-12 was recorded as blocked on a capture because Kewpie's own site serves the old design for that JAN. An independent retailer listing carries the current one, and it matches the shelf facings exactly (verified by eye against a crop of add/image6.jpg before enrolling). Measured effect on the corrected labels: live decision 60% -> 64%, end-to-end 59% -> 62%, full-resolution decision 81% -> 83%. Suite still 307. Also lands 12 more external-proxy images (six SKUs, two source domains each) and their scored result. Across both external sets - 20 images - the lane is 13 correct, 7 abstain, 0 false accepts.		2026-09-29 03:22:03 +09:00
..
evaluations/2026-09-29-session	docs(decision): refresh every number the corrected labels moved	2026-09-29 03:18:30 +09:00
external-eval	fix(catalog): enroll the current l06 package, closing F-12	2026-09-29 03:22:03 +09:00
packshots	fix(catalog): enroll the current l06 package, closing F-12	2026-09-29 03:22:03 +09:00
README.md	Enroll from a repo data dir; read packshots in every orientation	2026-09-29 02:33:47 +09:00

README.md

Recognition data

Everything the identity work needs to be reproducible: sourced packshots, evaluation runs, and the audits that produced them. Nothing here is ephemeral; a run that matters is written here, not to a temp directory.

`packshots/source/`

Front packshots as downloaded, before enrollment. ATTRIBUTION.json records the source URL, the product as printed, and the manufacturer for each. ocr-reads.json holds the OCR text each image produced, so a name/OCR refusal can be re-checked without re-running Vision.

rebuild_catalog.py reads this directory and writes a catalog:

.venv/bin/python code/rebuild_catalog.py --source data/packshots/source \
    --output stock-lopia-clean --csv stock-lopia/stock.csv --min-views 1 --replace

`evaluations/`

One directory per session. Each holds the raw artifacts a claim was computed from, so a number in DECISION.md can be traced back to the run that produced it.

Directory	Contents
`stream/`	WebSocket track dumps from `stream_client.py`, scored by `score_stream.py`.
`still/`	`/v1/recognize` responses for the still-image path.
`catalog-audit/`	`rebuild_catalog.py --json` reports.
`scratch/`	Intermediate images (rotations, crops) kept because they document a finding.

Scoring a stream dump:

.venv/bin/python code/score_stream.py data/evaluations/<session>/stream/<file>.json \
    --labels eval/labels/image6.json --stock-dir stock-lopia-clean