Update app.py

app.py

@@ -59,67 +59,35 @@ def triage(label, conf, text):
 CFG = load_json("fusion_config.json")
 LABEL_MAP = load_json("label_map.json")
 
-# label_map can be {"label": idx} or {"0":"label"}
-
-def normalize_label(x):
-    """
-    Makes label_map robust:
-    - ["eczema"] -> "eczema"
-    - "['eczema']" -> "eczema"
-    - [] / "" / None -> "unknown"
-    """
-    if x is None:
-        return "unknown"
-    if isinstance(x, list):
-        return normalize_label(x[0]) if len(x) else "unknown"
-    s = str(x).strip()
-    if s == "" or s.lower() in ["none", "nan", "null"]:
-        return "unknown"
-    if s.startswith("[") and s.endswith("]"):
-        try:
-            return normalize_label(ast.literal_eval(s))
-        except Exception:
-            pass
-    return s.lower()
-
-def build_classes(label_map):
-    if not isinstance(label_map, dict) or len(label_map) == 0:
-        raise ValueError("label_map.json must be a non-empty dict")
-
-    keys = list(label_map.keys())
-    vals = list(label_map.values())
-
-    # Case A: {"0":"eczema", "1":"acne"}  (idx -> label)
-    if all(isinstance(k, str) and k.isdigit() for k in keys):
-        idx2label = {int(k): normalize_label(v) for k, v in label_map.items()}
-        classes = [idx2label[i] for i in sorted(idx2label.keys())]
-        return classes
-
-    # Case B: {"eczema":0, "acne":1}  (label -> idx)
-    if all(isinstance(v, (int, float)) and float(v).is_integer() for v in vals):
-        label2idx = {normalize_label(k): int(v) for k, v in label_map.items()}
-        classes = [lab for lab, _ in sorted(label2idx.items(), key=lambda x: x[1])]
-        return classes
-
-    # Case C: weird format like {"eczema": ["eczema"], ...}
-    # Use KEYS as labels (dedup + sorted)
-    classes = sorted({normalize_label(k) for k in keys})
-    return classes
-
-CLASSES = build_classes(LABEL_MAP)
-NUM_CLASSES = len(CLASSES)
-
-print("✅ NUM_CLASSES:", NUM_CLASSES)
-print("✅ First labels:", CLASSES[:10])
+# ✅ your label_map.json is a wrapper: {"classes":[...], "label2idx":{...}}
+if isinstance(LABEL_MAP, dict) and "classes" in LABEL_MAP and "label2idx" in LABEL_MAP:
+    CLASSES = [str(x).strip().lower() for x in LABEL_MAP["classes"]]
+    label2idx = {str(k).strip().lower(): int(v) for k, v in LABEL_MAP["label2idx"].items()}
+
+    # (optional but good) sanity check: classes order matches label2idx
+    if len(CLASSES) != len(label2idx):
+        raise ValueError("label_map.json mismatch: len(classes) != len(label2idx)")
+    for i, lab in enumerate(CLASSES):
+        if label2idx.get(lab, None) != i:
+            # if mismatch, rebuild CLASSES from label2idx index order
+            idx2label = {int(v): str(k).strip().lower() for k, v in LABEL_MAP["label2idx"].items()}
+            CLASSES = [idx2label[i] for i in sorted(idx2label.keys())]
+            break
+
+else:
+    # Fallback: support plain formats too
+    if all(isinstance(k, str) and k.isdigit() for k in LABEL_MAP.keys()):  # {"0":"eczema",...}
+        idx2label = {int(k): str(v).strip().lower() for k, v in LABEL_MAP.items()}
+        CLASSES = [idx2label[i] for i in sorted(idx2label.keys())]
+        label2idx = {c: i for i, c in enumerate(CLASSES)}
+    else:  # {"eczema":0,...}
+        label2idx = {str(k).strip().lower(): int(v) for k, v in LABEL_MAP.items()}
+        CLASSES = [c for c, _ in sorted(label2idx.items(), key=lambda x: x[1])]
 
-IMG_BACKBONE = CFG.get("img_backbone", "tf_efficientnetv2_s")
-IMG_SIZE = int(CFG.get("img_size", 384))
-TEXT_MODEL_NAME = CFG.get(
-    "text_model_name",
-    "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext"
-)
-MAX_LEN = int(CFG.get("max_len", 128))
+NUM_CLASSES = len(CLASSES)
 
+print("✅ NUM_CLASSES:", NUM_CLASSES)          # should print 16
+print("✅ First labels:", CLASSES[:5])         # sanity check
 
 IMG_BACKBONE = CFG.get("img_backbone", "tf_efficientnetv2_s")
 IMG_SIZE = int(CFG.get("img_size", 384))