Update app.py

app.py

@@ -49,17 +49,30 @@ def metrics_markdown():
     if not p.exists():
         return "_metrics.json not found._"
     m = json.loads(p.read_text())
-    out = [
-        f"**Test accuracy:** {m['test_accuracy']:.2%}  ·  "
-        f"**Macro F1:** {m['macro_f1']:.3f}  ·  "
-        f"**Best val accuracy:** {m['best_val_accuracy']:.2%}  ·  "
-        f"**Parameters:** {m['params']:,}",
-        "",
-        "| Class | Precision | Recall | F1 | Test images |",
-        "|---|---|---|---|---|",
-    ]
-    for c, r in m["per_class"].items():
-        out.append(f"| {c} | {r['precision']:.3f} | {r['recall']:.3f} | {r['f1-score']:.3f} | {int(r['support'])} |")
+    cm = np.array(m["confusion_matrix"])
+    tp = cm.diagonal()
+    precision = tp / cm.sum(axis=0).clip(min=1)
+    recall    = tp / cm.sum(axis=1).clip(min=1)
+    f1        = 2 * precision * recall / (precision + recall + 1e-12)
+
+    head = [f"**Test accuracy:** {m['test_accuracy']:.2%}",
+            f"**Macro F1:** {m['macro_f1']:.3f}"]
+    if m.get("best_val_accuracy"):
+        head.append(f"**Best val accuracy:** {m['best_val_accuracy']:.2%}")
+    if m.get("params"):
+        head.append(f"**Parameters:** {m['params']:,}")
+
+    out = ["  ·  ".join(head), "",
+           "| Class | Precision | Recall | F1 | Test images |",
+           "|---|---|---|---|---|"]
+    for i, c in enumerate(CLASSES):
+        out.append(f"| {c} | {precision[i]:.3f} | {recall[i]:.3f} | {f1[i]:.3f} | {cm[i].sum()} |")
+
+    # top confusions
+    off = [(cm[i, j], CLASSES[i], CLASSES[j]) for i in range(len(CLASSES))
+           for j in range(len(CLASSES)) if i != j]
+    out += ["", "**Most confused (actual → predicted):** " +
+            ", ".join(f"{a} → {b} ({n})" for n, a, b in sorted(off, reverse=True)[:4])]
     return "\n".join(out)
 
 PLOTS = [