WeightsUnpickler error in segment/predict.py

[sanatani11]

Hello sir
I am trying to run the command :
%cd {HOME}/yolov7/seg !python segment/predict.py --weights $WEIGHTS_PATH --source $IMAGE_PATH --name coco

It gives an error; I also attached the image of it.
Traceback (most recent call last):
File "/content/yolov7/seg/segment/predict.py", line 265, in
main(opt)
File "/content/yolov7/seg/segment/predict.py", line 260, in main
run(**vars(opt))
File "/usr/local/lib/python3.11/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/content/yolov7/seg/segment/predict.py", line 95, in run
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/content/yolov7/seg/models/common.py", line 404, in init
model = attempt_load(weights if isinstance(weights, list) else w, device=device, inplace=True, fuse=fuse)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/content/yolov7/seg/models/experimental.py", line 79, in attempt_load
ckpt = torch.load(attempt_download(w), map_location='cpu') # load
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/serialization.py", line 1470, in load
raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
_pickle.UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the weights_only argument in torch.load from False to True. Re-running torch.load with weights_only set to False will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with weights_only=True please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL models.yolo.SegmentationModel was not an allowed global by default. Please use torch.serialization.add_safe_globals([SegmentationModel]) or the torch.serialization.safe_globals([SegmentationModel]) context manager to allowlist this global if you trust this class/function.

Could you please guide me to get out of it, please?
Thanks
Raushan

[RolandasRazma]

downgrade torch to 2.5.1

[Aayan-Ali-Hashim]

!pip uninstall torch torchvision !pip install "torchvision<0.20" !pip install "torch<2.6.0"

Run these commands before the execution of your code.