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

A question of "no attribute" error #49

Open Zheng-Yi-git opened 2 years ago

Zheng-Yi-git commented 2 years ago

Hi, I was trying to replicate the results with your code. But when it comes to the "fine" part, the code render_kwargs_train['network_fine'].state_dict() always leaves me an error like 'NoneType' object has no attribute 'state_dict', I don't know the reason. As I'm a beginner, I sincerely hope you can help me out. Much thanks!

jhq1234 commented 2 years ago

I have the same problem too! Hopely it will be solved fast!

lachholden commented 2 years ago

This occurs if --N_importance is not set, which essentially disables the fine network, and the checkpointing code doesn't handle this properly.

NJUSTUDY commented 4 months ago

Hello, I also have the same problem. What are the following solutions