Update app.py

app.py

@@ -39,23 +39,26 @@ def grad_cam(model, img, size, preprocess_func):
         conv_outputs, predictions = grad_model(x_tensor)
         loss = predictions[:, 0]
     grads = tape.gradient(loss, conv_outputs)
-    cam = tf.reduce_mean(grads, axis=-1).numpy()
-    cam = np.squeeze(cam)
 
-    cam = np.maximum(cam, 0)
-    cam = cam / cam.max() if cam.max() != 0 else cam
-    heatmap = cv2.resize(cam, size)
-    heatmap = np.uint8(255 * heatmap)
+    cam = tf.reduce_mean(grads, axis=-1)[0]  # (H, W)
+    cam = tf.maximum(cam, 0)
+    cam = cam / tf.reduce_max(cam + tf.keras.backend.epsilon())
+    cam = cam.numpy()  # ✅ convert to numpy before resizing
+
+    cam = cv2.resize(cam, size)
+    heatmap = np.uint8(255 * cam)
     heatmap = cv2.applyColorMap(heatmap, cv2.COLORMAP_JET)
 
     img_np = np.array(img_resized)
-    if img_np.shape[-1] == 4:
+    if img_np.shape[-1] == 4:  # remove alpha if present
         img_np = img_np[:, :, :3]
+
     superimposed = cv2.addWeighted(img_np, 0.6, heatmap, 0.4, 0)
     return Image.fromarray(cv2.cvtColor(superimposed, cv2.COLOR_BGR2RGB))
 
 
 
+
 # Preprocessing helper
 def preprocess(img, size, func):
     img = img.resize(size)