search

LLNL / MuyGPyS

A fast, pure python implementation of the MuyGPs Gaussian process realization and training algorithm.
Other
23 stars 11 forks source link

Quick fix to add homoscedasticity to torch functions #85

Closed alecmdunton closed 1 year ago

alecmdunton commented 1 year ago

Update torch API

bwpriest commented 1 year ago

I didn't catch this gap when I wrote PR #80. Is MuyGPyS.torch not covered by any test cases? If not, we should add some to ensure that this sort of thing doesn't happen again.

bwpriest commented 1 year ago

I didn't catch this gap when I wrote PR #80. Is MuyGPyS.torch not covered by any test cases? If not, we should add some to ensure that this sort of thing doesn't happen again.

We should probably put tests for MuyGPyS.torch in a tests/torch.py to start.

alecmdunton commented 1 year ago

I didn't catch this gap when I wrote PR #80. Is MuyGPyS.torch not covered by any test cases? If not, we should add some to ensure that this sort of thing doesn't happen again.

We should probably put tests for MuyGPyS.torch in a tests/torch.py to start.

Let me confirm this - I am pretty sure I covered that module in the test bed.