KeyError: 'frames_tracked_per_obj' #219 #239
Description
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
{'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], 'fps': 30, 'replace_flag': True, 'retarget_flag': False, 'use_flux': False, 'iterations': 3, 'k': 7, 'w_len': 1, 'h_len': 1}
frame_num: 106
video_fps: 30.0
fps: 30
target_num: 106
2025-10-17 08:20:44.839 | INFO | process_pipepline:call:67 - Processing pose meta
2025-10-17 08:20:51.165 | INFO | process_pipepline:call:82 - Processing reference image: ./examples/wan_animate/replace/image.jpeg
2025-10-17 08:20:51.209 | INFO | process_pipepline:call:89 - Processing template video: ./examples/wan_animate/replace/video.mp4
video frame: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 106/106 [00:02<00:00, 39.27it/s]
Traceback (most recent call last):
File "/home/ubuntu/Wan2.2/./wan/modules/animate/preprocess/preprocess_data.py", line 109, in
process_pipeline(video_path=args.video_path,
File "/home/ubuntu/Wan2.2/wan/modules/animate/preprocess/process_pipepline.py", line 97, in call
masks = self.get_mask(frames, 400, tpl_pose_metas)
File "/home/ubuntu/Wan2.2/wan/modules/animate/preprocess/process_pipepline.py", line 319, in get_mask
self.predictor.reset_state(inference_state)
File "/home/ubuntu/miniconda3/envs/wan/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/home/ubuntu/Wan2.2/sam2/sam2/sam2_video_predictor.py", line 678, in reset_state
self._reset_tracking_results(inference_state)
File "/home/ubuntu/Wan2.2/sam2/sam2/sam2_video_predictor.py", line 701, in _reset_tracking_results
for v in inference_state["frames_tracked_per_obj"].values():
KeyError: 'frames_tracked_per_obj'