search

yenchenlin / nerf-pytorch

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
MIT License
5.37k stars 1.04k forks source link

About network. #71

Closed calmelo closed 2 years ago

calmelo commented 2 years ago

self.pts_linears = nn.ModuleList( [nn.Linear(input_ch, W)] + [nn.Linear(W, W) if i not in self.skips else nn.Linear(W + input_ch, W) for i in range(D-1)])

Why (D-1) instead of D? There are 8 fully-connected ReLU layers in the paper, why did you use 7 layers?

ttaoREtw commented 2 years ago

Actually, the total number is 8 as in NeRF paper. You miss the first one [nn.Linear(input_ch, W)].

yenchenlin commented 2 years ago

Yes, thanks @ttaoREtw and good question @calmelo !