|
Some checks failed
tests / model-free (pull_request) Has been cancelled
The protocol asks for a source at least 800px tall so a view can be stored as a 200/400/800px pyramid. Nothing enforced it, and the clean catalog's l09 view is 305px - the documented defect where its inlier scores dwarf every other reference (85-129 against 10-40) and it wins facings it should not. Reported, not refused: the view is usable and dropping it would remove the SKU from the catalog entirely, which is worse than an incomparable score. The fix is re-sourcing the packshot, which is a data task. The check names the view and its height so the re-sourcing has a target. Suite 272 -> 274. |
||
|---|---|---|
| .. | ||
| web | ||
| __init__.py | ||
| app.py | ||
| bench_engine.py | ||
| bench_identity.py | ||
| build_store_from_shelf.py | ||
| collect_shelf_images.py | ||
| detector.py | ||
| empty_shelf_detector.py | ||
| engine.py | ||
| eval_external_images.py | ||
| eval_identity.py | ||
| eval_live.py | ||
| feature_matcher.py | ||
| finetune_identity.py | ||
| gallery.py | ||
| identity.py | ||
| identity_lanes.py | ||
| inventory.py | ||
| live.py | ||
| ocr.py | ||
| rebuild_catalog.py | ||
| reconcile.py | ||
| record.py | ||
| shelf_map.py | ||
| stream_client.py | ||
| tag_cards.py | ||
| tags.py | ||
| test_api.py | ||
| test_engine.py | ||
| test_eval_live.py | ||
| test_gallery.py | ||
| test_identity.py | ||
| test_live.py | ||
| test_ocr_tags.py | ||
| test_real_model.py | ||
| test_rebuild_catalog.py | ||
| test_reconcile.py | ||
| test_record.py | ||
| test_shelf_map.py | ||
| test_tag_cards.py | ||
| test_tag_identity.py | ||
| test_tracking.py | ||
| tracking.py | ||
| train.py | ||
| transport.py | ||