search

albertpumarola / D-NeRF

MIT License
536 stars 67 forks source link

low efficiency #7

Closed ray8828 closed 2 years ago

ray8828 commented 2 years ago

Hi, thanks for sharing this interesting work. I don't know whether it's the problem of the implementation, but the training can only reach around 15% util of an RTX-2080ti, and as a result extremely slow compared to the standard nerf-pytorch implementation, is this what we should expect?

Thanks

ray8828 commented 2 years ago

For some reason, in the helper file the autograd anormaly mode has been turned on in current version, which leads to extremely low efficiency