video frame: 100%|████████████████████████████████████████████████████████████████████████| 205/205 [00:04<00:00, 47.13it/s]
Traceback (most recent call last):
File "/root/Wan-Animate/Wan2.2/wan/modules/animate/preprocess/preprocess_data.py", line 109, in <module>
process_pipeline(video_path=args.video_path,
File "/root/Wan-Animate/Wan2.2/wan/modules/animate/preprocess/process_pipepline.py", line 97, in call
masks = self.get_mask(frames, 400, tpl_pose_metas)
File "/root/Wan-Animate/Wan2.2/wan/modules/animate/preprocess/process_pipepline.py", line 319, in get_mask
self.predictor.reset_state(inference_state)
File "/root/Wan-Animate/.venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, kwargs)
File "/root/Wan-Animate/segment-anything-2/sam2/sam2_video_predictor.py", line 678, in reset_state
self._reset_tracking_results(inference_state)
File "/root/Wan-Animate/segment-anything-2/sam2/sam2_video_predictor.py", line 701, in resettracking_results
for v in inference_state["frames_tracked_per_obj"].values():
KeyError: 'frames_tracked_per_obj'
stuck at above error when running command for replacement mode -
python wan/modules/animate/preprocess/preprocess_data.py
--ckpt_path Wan2.2-Animate-14B/process_checkpoint
--video_path examples/wan_animate/replace/video.mp4
--refer_path examples/wan_animate/replace/image.jpeg
--save_path examples/wan_animate/replace/process_results
--resolution_area 1280 720
--iterations 3
--k 7
--w_len 1
--h_len 1
--replace_flag