Update app.py

app.py

@@ -100,23 +100,27 @@ def make_gradcam(img_path, model, last_conv_layer_name="conv5_block32_concat", c
 
 # ---- Fonction Gradio ----
 def gradio_predict(image_file):
+    # Prédiction
     probs = predict_single(image_file)
 
-    sorted_idx = np.argsort(-probs)
-    sorted_labels = [CLASS_NAMES[i].upper() for i in sorted_idx]
-    sorted_probs = probs[sorted_idx] * 100
-
+    # Classe globale
     benign_prob = sum(probs[i] for i, cls in enumerate(CLASS_NAMES) if diagnosis_map[cls] == "Bénin")
     malign_prob = sum(probs[i] for i, cls in enumerate(CLASS_NAMES) if diagnosis_map[cls] == "Malin")
     global_diag = "Bénin" if benign_prob >= malign_prob else "Malin"
 
-    bar_data = {"Classes": sorted_labels, "Probabilité (%)": sorted_probs.tolist()}
+    # BarPlot
+    sorted_idx = np.argsort(-probs)
+    sorted_labels = [CLASS_NAMES[i].upper() for i in sorted_idx]
+    sorted_probs = (probs[sorted_idx] * 100).tolist()
+    bar_data = {"Classes": sorted_labels, "Probabilité (%)": sorted_probs}
 
-    # Grad-CAM sur la meilleure classe
+    # Grad-CAM
     top_class = np.argmax(probs)
     gradcam_img = make_gradcam(image_file, model_densenet, class_index=top_class)
 
-    return global_diag, gr.BarPlot.update(value=bar_data, x="Classes", y="Probabilité (%)", title="Distribution des classes"), gradcam_img
+    # ✅ Retour exact attendu par Gradio
+    return global_diag, bar_data, gradcam_img
+
 
 # ---- Gradio UI ----
 examples = [