Hi,
I have trained a model on windows. But I tried load this pretrained model on Ububntu. I got the error. I am in fastai latest version ( fastai 2.1.5)
python 3.8
the code is the following
load_learn = load_learner(fname=‘86_91.pkl’, cpu=False)
where 86_91.pkl is a trained model which is in my current directory
The error message I am getting is following. Not sure how to proceed with this error. Anyone have the idea how to proceed further
NotImplementedError Traceback (most recent call last)
in
1 model_path=Path.cwd()
----> 2 load_learn = load_learner(fname=‘86_91.pkl’, cpu=False)
~/anaconda3/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in load_learner(fname, cpu)
549 "Load a Learner object in fname, optionally putting it on the cpu"
550 distrib_barrier()
–> 551 res = torch.load(fname, map_location=‘cpu’ if cpu else None)
552 if hasattr(res, ‘to_fp32’): res = res.to_fp32()
553 if cpu: res.dls.cpu()
~/anaconda3/envs/fastai/lib/python3.8/site-packages/torch/serialization.py in load(f, map_location, pickle_module, **pickle_load_args)
592 opened_file.seek(orig_position)
593 return torch.jit.load(opened_file)
–> 594 return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
595 return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
596
~/anaconda3/envs/fastai/lib/python3.8/site-packages/torch/serialization.py in _load(zip_file, map_location, pickle_module, pickle_file, **pickle_load_args)
851 unpickler = pickle_module.Unpickler(data_file, **pickle_load_args)
852 unpickler.persistent_load = persistent_load
–> 853 result = unpickler.load()
854
855 torch._utils._validate_loaded_sparse_tensors()
~/anaconda3/envs/fastai/lib/python3.8/pathlib.py in new(cls, *args, **kwargs)
1038 self = cls._from_parts(args, init=False)
1039 if not self._flavour.is_supported:
-> 1040 raise NotImplementedError(“cannot instantiate %r on your system”
1041 % (cls.name,))
1042 self._init()
NotImplementedError: cannot instantiate ‘WindowsPath’ on your system
Any help is highly appreciated