search

Yzmblog / MonoHuman

MonoHuman: Animatable Human Neural Field from Monocular Video (CVPR 2023)
135 stars 9 forks source link

How much memory of GPU is needed for training? #8

Closed garrisonz closed 1 year ago

garrisonz commented 1 year ago

I train Monohuman on a single 16G P100, but it fail with error "cuda out of memory". May I know how much memory of GPU is needed when training. thanks

garrisonz commented 1 year ago

around 30G. 32G v100 is good enough.

Yzmblog commented 1 year ago

I train Monohuman on a single 16G P100, but it fail with error "cuda out of memory". May I know how much memory of GPU is needed when training. thanks

Hi, if your CUDA memory is not enough, you can reduce the N_patches and size configs and increase sample_subject_ratio configs in https://github.com/Yzmblog/MonoHuman/blob/main/configs/default.yaml#LL132C1-L135C40 to fit your machine.