product-recognition-demo/recognization/code
kiyo9w 5eb4bdf6c8 chore(eval): reconcile the distractor sets and refresh the sweep numbers
The Wikimedia collector truncated the whole basename at 60 characters, so 13
files lost their extension and cv2 could not read them by name - the distractor
sets were quietly scoring 13 images fewer than they held. It now truncates the
stem and keeps the extension, and the files on disk are renamed to match.

The search terms also pull in .djvu volumes whose page 1 Commons serves as a
JPEG thumbnail. Twelve book scans were in the sets; they contributed 0 false
accepts, and they are not shelves, so the collector filters them and the
manifests no longer list them.

With all 2650 crops readable the sweep is re-measured end to end: 3.09% at the
old lines, 0.30% at the shipped 4.0/4, image6 44 shown / 42 correct / 95.5%.
The accept sweep table and the verdict's far-unknown sentence now carry those
numbers instead of the pre-calibration ones.

Also: the fetched images are gitignored (manifests and results are not), the
l10/l11 shelf-tag crops that back the catalog corrections are committed, and a
stale pre-gate eval.json and a duplicate of eval/labels/image6.json are gone.
2026-09-29 04:17:54 +09:00
..
web fix: restore reliable authenticated live recognition 2026-09-28 12:38:15 +09:00
__init__.py
app.py fix(eval): confirm a leak signature before calling it one, and score external sets in code 2026-09-29 03:29:56 +09:00
bench_engine.py feat: recognition engine and session tracker for multi-client serving 2026-09-24 11:52:59 +09:00
bench_identity.py feat: a multi-view embedding gallery, because one template per SKU cannot work 2026-09-24 23:43:27 +09:00
build_store_from_shelf.py fix: require explicit safe shelf enrollment paths 2026-09-28 13:41:43 +09:00
collect_shelf_images.py chore(eval): reconcile the distractor sets and refresh the sweep numbers 2026-09-29 04:17:54 +09:00
detector.py
empty_shelf_detector.py
engine.py fix(eval): confirm a leak signature before calling it one, and score external sets in code 2026-09-29 03:29:56 +09:00
eval_distractors.py fix(identity): calibrate both accept lines against unrelated shelves 2026-09-29 04:08:59 +09:00
eval_external.py feat(eval): report the external benchmark per SKU 2026-09-29 03:37:04 +09:00
eval_external_images.py fix(catalog): correct sku_l10 to 400g and enroll its packshot 2026-09-29 02:45:21 +09:00
eval_identity.py feat(eval): add --no-text so the E-3 claim is reproducible 2026-09-29 03:32:38 +09:00
eval_live.py docs: name the local lane in the evaluators' own lane vocabulary 2026-09-28 22:34:06 +09:00
feature_matcher.py feat: recognition server API, reference stream client, and live label memory 2026-09-24 12:31:17 +09:00
finetune_identity.py fix(catalog): correct sku_l10 to 400g and enroll its packshot 2026-09-29 02:45:21 +09:00
gallery.py feat(identity): local-feature matcher plus text lane as the default backend 2026-09-28 22:27:21 +09:00
identity.py fix(identity): calibrate both accept lines against unrelated shelves 2026-09-29 04:08:59 +09:00
identity_lanes.py fix(identity): calibrate both accept lines against unrelated shelves 2026-09-29 04:08:59 +09:00
inventory.py
live.py fix(eval): confirm a leak signature before calling it one, and score external sets in code 2026-09-29 03:29:56 +09:00
ocr.py feat: add bounded crop evidence and keyed gallery cache 2026-09-28 15:49:34 +09:00
rebuild_catalog.py feat(enroll): report views with no recorded source 2026-09-29 03:35:41 +09:00
reconcile.py fix: a tag may not accuse on weak evidence, nor name a distant product 2026-09-25 01:30:03 +09:00
record.py fix: record and require the walk identity backend 2026-09-28 14:42:03 +09:00
score_stream.py Fix label frame mapping and reference upscaling; add the stream G1 harness 2026-09-29 00:30:17 +09:00
shelf_map.py feat: a shelf map, so a facing outlives the track id that found it 2026-09-25 01:54:38 +09:00
stream_client.py Fix label frame mapping and reference upscaling; add the stream G1 harness 2026-09-29 00:30:17 +09:00
tag_cards.py fix: restore reliable authenticated live recognition 2026-09-28 12:38:15 +09:00
tags.py fix: bind tag projection to each frame origin 2026-09-28 14:41:49 +09:00
test_api.py feat(identity): local-feature matcher plus text lane as the default backend 2026-09-28 22:27:21 +09:00
test_engine.py fix(identity): calibrate both accept lines against unrelated shelves 2026-09-29 04:08:59 +09:00
test_eval_labels.py feat: refuse a label file whose rows carry no provenance 2026-09-28 23:31:53 +09:00
test_eval_live.py fix: record and require the walk identity backend 2026-09-28 14:42:03 +09:00
test_gallery.py fix: serialize gallery inference so Metal cannot be entered twice 2026-09-28 17:22:55 +09:00
test_identity.py fix(eval): confirm a leak signature before calling it one, and score external sets in code 2026-09-29 03:29:56 +09:00
test_live.py Improve identity lanes: text evidence floor, motion-compensated labels 2026-09-29 02:08:23 +09:00
test_ocr_tags.py fix: bind tag projection to each frame origin 2026-09-28 14:41:49 +09:00
test_real_model.py docs: API contract, README for the server and live mode, real-model test 2026-09-24 12:46:54 +09:00
test_rebuild_catalog.py Enroll from a repo data dir; read packshots in every orientation 2026-09-29 02:33:47 +09:00
test_reconcile.py fix: a tag may not accuse on weak evidence, nor name a distant product 2026-09-25 01:30:03 +09:00
test_record.py fix: record and require the walk identity backend 2026-09-28 14:42:03 +09:00
test_shelf_map.py feat: a shelf map, so a facing outlives the track id that found it 2026-09-25 01:54:38 +09:00
test_tag_cards.py fix: the number on the tag is the regular price, and a price must be corroborated 2026-09-25 01:29:46 +09:00
test_tag_identity.py fix: a tag may not accuse on weak evidence, nor name a distant product 2026-09-25 01:30:03 +09:00
test_tracking.py test: defend engine and tracking contracts 2026-09-24 12:43:32 +09:00
tracking.py fix: restore reliable authenticated live recognition 2026-09-28 12:38:15 +09:00
train.py
transport.py fix: guard reserved sessions and bounded response state 2026-09-28 13:41:35 +09:00