Update app.py

app.py

@@ -186,8 +186,8 @@ def inference_and_return_video(dilation_iterations, num_inference_steps, video_s
     images = video_state["origin_images"]
     masks = video_state["masks"]
 
-    images = np.array(images)
-    masks = np.array(masks)
+    #images = np.array(images)
+    #masks = np.array(masks)
     print(f"line 191 images shape:{images.shape},masks shape:{masks.shape}")
     #line 191 images shape:(1, 1024, 1820, 3),masks shape:(1, 1024, 1820), which should be (16, 1024, 1820, 3) and (16, 1024, 1820, 3)
     img_tensor, mask_tensor = preprocess_for_removal(images, masks)
@@ -280,6 +280,8 @@ def track_video(n_frames, video_state):
         output_frames.append(painted)
         print(f"line 281 len(output_frames)={len(output_frames)}, painted shape:{painted.shape}")
     video_state["masks"] = 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"
     clip = ImageSequenceClip(output_frames, fps=15)
     clip.write_videofile(video_file, codec='libx264', audio=False, verbose=False, logger=None)