Open najafi1350 opened 1 year ago
Hello @najafi1350 ,
As stated in the readme: Our approach is designed for high-end NVIDIA GPUs with large amounts of memory. To run on mid-range GPU's, reduce the batch size parameter in the .json files.
The code relies on CUDA, so will only run on NVIDIA GPUs, and I would recommend 16GB or more of GPU memory. For the paper, we used V100 GPUs with 32 GB and A6000 with 48 GB.
We also use the tiny-cuda-nn library, and I refer to their documentation for GPU and cuda version requirements: https://github.com/NVlabs/tiny-cuda-nn
Our code should run fine on both Windows and Linux.
Hello dear What system is required to run the program? Such as CPU GPU &... thanks