You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm interested in running your code to reproduce the results presented in your paper. Could you please specify the hardware requirements? Specifically, I'm interested in the following:
RAM requirements
GPU memory (VRAM) requirements
Any other hardware dependencies
Would it be possible to achieve the paper's results using an NVIDIA RTX 3090 or 4090?
Thanks!
The text was updated successfully, but these errors were encountered:
thanks for your interest in NeRSemble.
The GPU requirements are listed in the README:
RTX A6000 GPU (48GB)
The biggest screw to get VRAM consumption down is probably the --n_hash_encodings flag because it controls the number of hash grids that are used. The default is 32 which we used for our results, but as we show in the paper, using 16 only slightly worsens the result, but it might almost half the required VRAM.
Regarding RAM requirements, it can go up to 200G but this is just due to caching in the dataloader (for speed reasons). If you don't have RAM lying around, you can easily reduce the caching. Per default, it caches 10k train samples, but you can turn that number down as much as you want. I added the --max_cached_images option to the train script for that. Thanks for the hint.
To exactly reproduce the paper results with the same architecture on a 24G GPU, your only chance currently would be to set the --max_n_samples_per_batch to a low value which will reduce the memory consumption of forward/backward passes, but make it quite slow. However, in the README you can also find official metrics as well as trained models which might be enough for your use-case?
Hello,
I'm interested in running your code to reproduce the results presented in your paper. Could you please specify the hardware requirements? Specifically, I'm interested in the following:
Would it be possible to achieve the paper's results using an NVIDIA RTX 3090 or 4090?
Thanks!
The text was updated successfully, but these errors were encountered: