Very minor but worth mentioning.

Pylint isn't picking up that torch has the member function from_numpy. It's because torch.from_numpy is actually torch._C.from_numpy as far as Pylint is concerned.

According to this stackoverflow thread numpy also suffers from this problem.

For reference, you can have Pylint ignore these by wrapping "problematic" calls with the following comments.

# pylint: disable=E1101
tensor = torch.from_numpy(np_array)
# pylint: enable=E1101