Fix usage of nonzero for PyTorch 1.7+

[mberr]

Is your feature request related to a problem? Please describe.
The usage of Tensor.nonzero() (without arguments) has been deprecated, cf. pytorch/pytorch#40187

At least in

pykeen/src/pykeen/evaluation/evaluator.py

Line 360 in 630d872

filter_batch = (entity_filter_test & relation_filter).nonzero()

we use the now deprecated version.

Describe the solution you'd like
Change all usages of nonzero to use to future-proof variant, i.e. in the above mentioned case

filter_batch = (entity_filter_test & relation_filter).nonzero(as_tuple=False) 

Describe alternatives you've considered
Keep it as it is. This might lead to problems once PyTorch removes the deprecated behaviour.

Additional context
Warning found in this notebook: https://gist.github.com/cthoyt/190233fd98a11306ceb13f2ee0e95a9e (scroll all the way to the bottom)