search

creiser / kilonerf

Code for KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs
471 stars 52 forks source link

How to execute model without CUDA extension installation #14

Open hdh4797 opened 2 years ago

hdh4797 commented 2 years ago

Thank you for your contribution.

Custom CUDA-based code implementation shows extremely high-speed NeRF execution. However, Is there any method to execute KiloNeRF without CUDA installation? Since my GPU environment seems not suitable to install your custom CUDA (kilonerf_cuda), I want to execute the code without custom CUDA-based acceleration. I just need the same functionality given by the kilonerf_cuda library.

Is there any method to execute your code without custom CUDA installation? I want to simulate the same functionality even though it is much slower than the current custom CUDA-based implementation.

(The code seems single NeRF training is possible without CUDA installation. However, early ray termination and early space skipping, multi NeRF training is not possible, I think.)

creiser commented 2 years ago

It is possible but I really don't recommend it because it will be a bigger effort than fixing the installation problems and it will be so slow that for instance training a model would take a week. What error do you get when you try to install the kilonerf_cuda package?