You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I've stumbled upon your idea of using sympy to generate CUDA code to compute spherical harmonics and its derivatives, which I found a really nice approach!
In case someone is interested, I've reworked that approach in a more generalized manner to generating auto-diffable spherical harmonics for PyTorch here
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hey,
I've stumbled upon your idea of using sympy to generate CUDA code to compute spherical harmonics and its derivatives, which I found a really nice approach!
In case someone is interested, I've reworked that approach in a more generalized manner to generating auto-diffable spherical harmonics for PyTorch here
https://github.com/cheind/torch-spherical-harmonics/
I'm using them in my (work-in-progress) pure PyTorch version of ngp
https://github.com/cheind/pure-torch-ngp
Beta Was this translation helpful? Give feedback.
All reactions