GPU Implementation

[RyanCodrai]

This is an enhancement. Given that CorEx utilises a semi-supervised approach it would be advantageous to have a GPU Implementation as the reduced wait for feedback would allow for more rapid development of topics. https://developer.nvidia.com/how-to-cuda-python

[gregversteeg]

Hi Ryan, that's a good idea. There's not a GPU implementation for the topic models, but some variations have been coded in PyTorch: https://github.com/hrayrhar/T-CorEx