Update app.py

app.py

@@ -189,6 +189,7 @@ def inference_and_return_video(dilation_iterations, num_inference_steps, video_s
     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)
     mask_tensor = mask_tensor[:,:,:,:1]
 
@@ -271,10 +272,13 @@ def track_video(n_frames, video_state):
             mask += out_mask
         mask = np.clip(mask, 0, 1)
         mask = cv2.resize(mask, (W_, H_))
+        print(f"line 275 mask shape:{mask.shape}")
         mask_frames.append(mask)
+        print(f"line 277 len(mask_frames)={len(mask_frames)}")
         painted = (1 - mask * 0.5) * frame + mask * 0.5 * color
         painted = np.uint8(np.clip(painted * 255, 0, 255))
         output_frames.append(painted)
+        print(f"line 281 len(output_frames)={output_frames}, painted shape:{painted.shape}")
     video_state["masks"] = mask_frames
     video_file = f"/tmp/{time.time()}-{random.random()}-tracked_output.mp4"
     clip = ImageSequenceClip(output_frames, fps=15)