When setting up the segment_anything_2_video environment, an error occurred, preventing the normal activation of label-studio-ml

[JalingHerny]

I want to use segment_anything_2_video in conjunction with label-studio for video annotation, but when I run label-studio-ml start .\segment_anything_2_video in the directory C:\Users\Admin\label-studio-ml-backend\label_studio_ml\examples, the following error occurs:

**Traceback (most recent call last): File "C:\Users\Admin\AppData\Local\Programs\Python\Python310\lib\site-packages\hydra_internal\instantiate_instantiate2.py", line 92, in _call_target return target(*args, **kwargs) File "C:\Users\Admin\label-studio-ml-backend\label_studio_ml\sam2\sam2\sam2_video_predictor.py", line 36, in init super().init(**kwargs) TypeError: SAM2Base.init() missing 3 required positional arguments: 'image_encoder', 'memory_attention', and 'memory_encoder'

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "C:\Users\Admin\label-studio-ml-backend\label_studio_ml\examples\segment_anything_2_video_wsgi.py", line 33, in from model import NewModel File "C:\Users\Admin\label-studio-ml-backend\label_studio_ml\examples\segment_anything_2_video\model.py", line 39, in predictor = build_sam2_video_predictor(MODEL_CONFIG, sam2_checkpoint) File "C:\Users\Admin\label-studio-ml-backend\label_studio_ml\sam2\sam2\build_sam.py", line 129, in build_sam2_video_predictor model = instantiate(cfg.model, recursive=True) File "C:\Users\Admin\AppData\Local\Programs\Python\Python310\lib\site-packages\hydra_internal\instantiate_instantiate2.py", line 226, in instantiate return instantiate_node( File "C:\Users\Admin\AppData\Local\Programs\Python\Python310\lib\site-packages\hydra_internal\instantiate_instantiate2.py", line 347, in instantiate_node return _call_target(target, partial, args, kwargs, full_key) File "C:\Users\Admin\AppData\Local\Programs\Python\Python310\lib\site-packages\hydra_internal\instantiate_instantiate2.py", line 97, in _call_target raise InstantiationException(msg) from e hydra.errors.InstantiationException: Error in call to target 'sam2.sam2_video_predictor.SAM2VideoPredictor': TypeError("SAM2Base.init() missing 3 required positional arguments: 'image_encoder', 'memory_attention', and 'memory_encoder'") full_key: model**

I have been trying for a while. Has anyone encountered the same issue? I need assistance. Thank you very much.

Path to execute SAM2 : C:\Users\Admin\label-studio-ml-backend\label_studio_ml\examples\segment_anything_2_video Installation path for SAM 2.1 development kit : C:\Users\Admin\label-studio-ml-backend\label_studio_ml\sam2

( OS : Windows 11 )

Here are the versions of the software : python => 3.10.11
torch => 2.4.1+cu118
torchvision => 0.19.1+cpu
cuda => 11.8