Update app.py

app.py

@@ -154,8 +154,6 @@ def predict():
         output[0, class_index].backward()
         cam = gradcam.generate(class_index)
         
-
-
         # ✅ Ensure cam is 2D
         if cam.ndim == 3:
             cam = cam[0]
@@ -164,18 +162,22 @@ def predict():
         cam = np.uint8(255 * cam)
         cam = cv2.resize(cam, (224, 224))
         
-        # ✅ Create overlay
+        # ✅ Create color overlay
         original_img = np.asarray(img.resize((224, 224)))
         heatmap = cv2.applyColorMap(cam, cv2.COLORMAP_JET)
-        
-        # ✅ Final overlay
         overlay = cv2.addWeighted(original_img, 0.6, heatmap, 0.4, 0)
-
+        
+        # ✅ Save color overlay
         gradcam_filename = f"gradcam_{timestamp}.png"
         gradcam_file_path = os.path.join(OUTPUT_DIR, gradcam_filename)
         cv2.imwrite(gradcam_file_path, overlay)
-
-        # ✅ Save results to SQLite
+        
+        # ✅ Save grayscale overlay
+        gray_filename = f"gradcam_gray_{timestamp}.png"
+        gray_file_path = os.path.join(OUTPUT_DIR, gray_filename)
+        cv2.imwrite(gray_file_path, cam)
+        
+        # ✅ Save results to database
         conn = sqlite3.connect(DB_PATH)
         cursor = conn.cursor()
         cursor.execute("""
@@ -184,7 +186,8 @@ def predict():
         """, (uploaded_filename, result, confidence, gradcam_filename, datetime.now().isoformat()))
         conn.commit()
         conn.close()
-
+        
+        # ✅ Return results
         return jsonify({
             'prediction': result,
             'confidence': confidence,
@@ -192,9 +195,9 @@ def predict():
             'early_glaucoma_probability': float(probabilities[1]),
             'advanced_glaucoma_probability': float(probabilities[2]),
             'gradcam_image': gradcam_filename,
+            'gradcam_gray_image': gray_filename,
             'image_filename': uploaded_filename
         })
-
     except Exception as e:
         return jsonify({'error': str(e)}), 500