search

bebeal / mipnerf-pytorch

A re-implementation of mip-NeRF in PyTorch
146 stars 15 forks source link

why does this implementation take 20 hours to train? #11

Closed ankan2709 closed 12 months ago

ankan2709 commented 1 year ago

When i run this model on a A100 gpu it takes about 20 hours to train where as the vanilla nerf took 4 hours? what is the reason behind this?