Closed apisarek closed 3 years ago
Yup, I think so - if I've written this correctly then everything should be differentiable. :)
I think this thread should be closed by now? Your work is for now by far the best solution for this problem! ;)
Yeah, it probably can. And thanks!
Hi!
I would like to ask whether it's possible and what would be the best approach to use your implementation to differentiate with respect to coefficients and/or coordinates of interpolated points.
Looking at the provided simple example I would like to backpropagate from
out
tox
- is it possible?