fix: restore reliable authenticated live recognition

recognization/code/finetune_identity.py

@@ -49,6 +49,88 @@ MILK_SHELF_LABELS = {
 }
 
 
+def enrollment_report(stock: str, csv_name: str = "stock.csv") -> dict:
+    """Catalog versus enrolled views. Does not load a model or write files.
+
+    A SKU with no readable view cannot be recognized. One view is reported, not
+    treated as enough: the measured knee is two views. Duplicate CSV rows and a
+    head whose class list disagrees with the catalog are blockers.
+    """
+    import csv
+    import re
+
+    from gallery import ProductGallery
+
+    names = []
+    try:
+        names = os.listdir(stock)
+    except OSError:
+        names = []
+    images = [name for name in names if os.path.splitext(name)[1].lower() in (".jpeg", ".jpg", ".png")]
+    rows = []
+    csv_path = os.path.join(stock, csv_name)
+    if os.path.exists(csv_path):
+        with open(csv_path, encoding="utf-8") as handle:
+            rows = list(csv.DictReader(handle))
+    sku_ids = []
+    seen = set()
+    duplicate_rows = []
+    for row in rows:
+        sku_id = (row.get("SKU_ID") or "").strip()
+        if not sku_id:
+            continue
+        if sku_id in seen:
+            duplicate_rows.append(sku_id)
+        seen.add(sku_id)
+        sku_ids.append(sku_id)
+    gallery = ProductGallery(stock, sku_ids or [])
+    views = {sku_id: gallery._views_for(sku_id) for sku_id in dict.fromkeys(sku_ids)}
+    missing = [sku_id for sku_id, paths in views.items() if not paths]
+    single = [sku_id for sku_id, paths in views.items() if len(paths) == 1]
+    claimed = {os.path.basename(path) for paths in views.values() for path in paths}
+    orphans = sorted(name for name in images if name not in claimed)
+    # ponytail: prefix collision check. A view named sku_001 must not also match sku_00.
+    collisions = []
+    for sku_id, paths in views.items():
+        bare = [os.path.basename(path) for path in paths if os.path.splitext(os.path.basename(path))[0] != sku_id
+                and not re.fullmatch(re.escape(sku_id) + r"[_-]\d+", os.path.splitext(os.path.basename(path))[0])]
+        if bare:
+            collisions.append(sku_id)
+    blockers = []
+    if duplicate_rows:
+        blockers.append("duplicate_csv_sku")
+    if missing:
+        blockers.append("sku_without_view")
+    if collisions:
+        blockers.append("view_prefix_collision")
+    head_path = os.path.join(stock, "identity_head.pt")
+    head_note = None
+    if os.path.exists(head_path):
+        head_note = "present_not_opened"
+        # Do not torch.load here: the head can be large, and this report must stay cheap.
+        # Class-list drift is reported when the caller passes class_ids.
+    return {
+        "stock": stock,
+        "sku_ids": list(dict.fromkeys(sku_ids)),
+        "images": len(images),
+        "missing": missing,
+        "single_view": single,
+        "orphans": orphans,
+        "duplicate_rows": duplicate_rows,
+        "collisions": collisions,
+        "blockers": blockers,
+        "head": head_note,
+    }
+
+
+def enrollment_report_text(report: dict) -> str:
+    return (
+        f"{report['stock']}: {len(report['sku_ids'])} SKUs, {report['images']} images, "
+        f"missing={len(report['missing'])}, single_view={len(report['single_view'])}, "
+        f"orphans={len(report['orphans'])}, blockers={report['blockers'] or 'none'}"
+    )
+
+
 def build_model(image_size: int = 518):
     import timm
     import torch
@@ -149,13 +231,13 @@ def train_from_stock(args) -> None:
     from gallery import ProductGallery
 
     stock = args.stock
-    gallery = ProductGallery(stock, [])
-    # the SKUs are whatever the stock directory holds
-    skus = sorted({os.path.splitext(name)[0].rsplit("_", 1)[0] if os.path.splitext(name)[0].rsplit("_", 1)[-1].isdigit()
-                   else os.path.splitext(name)[0]
-                   for name in os.listdir(stock)
-                   if os.path.splitext(name)[1].lower() in (".jpeg", ".jpg", ".png")})
-    views = {sku: gallery._views_for(sku) for sku in skus}
+    report = enrollment_report(stock)
+    print(enrollment_report_text(report))
+    if report["blockers"]:
+        print(f"{stock}: not training; enrollment blockers: {', '.join(report['blockers'])}")
+        return
+    gallery = ProductGallery(stock, report["sku_ids"])
+    views = {sku: gallery._views_for(sku) for sku in report["sku_ids"]}
     views = {sku: paths for sku, paths in views.items() if paths}
     if len(views) < 2:
         print(f"{stock}: needs at least two products with views, found {len(views)}")