Torchfields

------

* get_vote_weights_*: use softmax to avoid overflow issues

------

* Priority Vote: Adjusting kernel size for priority vote operations will now affect blurring
* Priority Vote: Consensus threshold can be 0

------

* Add priority\_vote
* Add vote\_with\_distances
* Add voting\_with\_variances to include prior weights

------

* feat(use\_identity\_mapping\_cache): allow caching identity\_mapping() results
* fix: 0.7.0 compatibility (8)
* Update license in setup.cfg

------

* Update documentation for sample()
* Allow non-square displacement fields
* Clean up identity mapping code
* Remove caching of identity mappings
* Use align\_corners=False from PyTorch 1.3.0 Will no longer work with earlier PyTorch versions
* Convert to using MIT License

------

* Prevent producing NaN in inverse backward pass
* Allow accessing field type as torchfields.Field
* Ensure contiguous gradients in inversion backward pass
* Allow padding to be explicitly given in \_pad()
* Bump required pytorch version to 1.1.0
* Factor out voting, inversion, and util functions
* Update README.md
* Update README.md