Giters

Ivan-Tang-3D / Any2Point

[ECCV2024] Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Question about training device

plusgrey opened this issue · comments

commented

Hi,

Thanks for your excellent work. May I know the number of GPUs and the specific device name of your training process?

commented

Hi,

Thanks for your excellent work. May I know the number of GPUs and the specific device name of your training process?

We train the whole models on one A100 80G GPU. However, the training of CLIP Text Encoder could run on GPU with memory>28G. The remaining codes and models I will release these days.