Update app.py

app.py

@@ -242,7 +242,7 @@ def track_video(n_frames, video_state):
         W_ = int(H_ * images[0].shape[1] / images[0].shape[0])
 
     images = [cv2.resize(img, (W_, H_)) for img in images]
-    video_state["origin_images"] = images
+    video_state["origin_images"] = np.array(images)##images
     images = np.array(images)
     inference_state = video_predictor.init_state(images=images/255, device=device)
     video_state["inference_state"] = inference_state
@@ -279,7 +279,7 @@ def track_video(n_frames, video_state):
         painted = np.uint8(np.clip(painted * 255, 0, 255))
         output_frames.append(painted)
         print(f"line 281 len(output_frames)={len(output_frames)}, painted shape:{painted.shape}")
-    video_state["masks"] = mask_frames
+    video_state["masks"] =np.array( mask_frames)
     print(f'line 283 len video_state["masks"]:{len(video_state["masks"])}')
     print(f'line 284 video_state["masks"][0].shape:{video_state["masks"][0].shape}')
     video_file = f"/tmp/{time.time()}-{random.random()}-tracked_output.mp4"