search

sail-sg / Consistent3D

The official PyTorch implementation of Consistent3D (CVPR 2024)
MIT License
62 stars 0 forks source link

Can not run inference on a single RTX3090 #6

Closed Colezwhy closed 2 months ago

Colezwhy commented 2 months ago

Thank you for your great job, but when I want to run inference on one single RTX3090, I got out of memory. Would you please provide some suggestions?

nickwzk commented 2 months ago

Hi @Colezwhy, Thank you for your interest in our work. You can simply try to reduce _batchsize to 4 in the configs to reduce the memory cost.

Colezwhy commented 2 months ago

Hi @Colezwhy, Thank you for your interest in our work. You can simply try to reduce _batchsize to 4 in the configs to reduce the memory cost.

Thank you, I will try.