This function should only be used to load models saved in python.
For it to work correctly you need to use torch.save with the flag:
_use_new_zipfile_serialization=True and also remove all nn.Parameter
classes from the tensors in the dict.
Usage
load_state_dict(path)
Value
a named list of tensors.
Arguments
path
to the state dict file
Details
The above might change with development of this
in pytorch's C++ api.