feat(backend): diff-vs-previous-run reporting for product-scan accuracy harness
Ports the DO-harness's auto-diff-vs-previous-run reporting into accuracy-check-scan.mts: prints a per-field, per-split (Training/ Validation) delta against the last product_accuracy_history.jsonl entry and calls out regressions/improvements explicitly, plus classifier method distribution and average confidence as informational context. Also adds the real held-out validation photo set into sources/product-test-images/ (75 photos, one per current SKU class) with its README documenting the drop-photo -> label -> re-run workflow, so the harness's Validation Set split actually has images to score against. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Xsxk4ZkDQVVaLUcixDcqb5
This commit is contained in:
1 parent
dc0dd81318
commit
3a17c28758
78 files changed
+306
-55
No files matched your search
BIN
Binary file not shown.
|
After Width: | Height: | Size: 4.1 MiB |
Reference in new issue
Block a user