VITA-Group / GNT

[ICLR 2023] "Is Attention All NeRF Needs?" by Mukund Varma T*, Peihao Wang* , Xuxi Chen, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang
https://vita-group.github.io/GNT
MIT License
338 stars 24 forks source link

cuda out of memory #3

Closed CCOSerika closed 2 years ago

CCOSerika commented 2 years ago

Hi, author. Thanx for your great work! I cannot wait to see how it will work. I train on my RTX3090 but it gives "cuda out of memory". Could u kindly provide the trained ckpts with us to check? Or how can I set the parameters to run it successfully. Looking forward to your reply!

CCOSerika commented 2 years ago

By the way, what graphics card did u use for training? Will RTX3090 be okey?

MukundVarmaT commented 2 years ago

Thank you for your interest in our work. We have released the pre-trained models here. We run all our experiments on RTX A6000 cards (with 48G memory). You could try reducing the N_rand parameter to train the model on smaller cards.

CCOSerika commented 2 years ago

I got it. Thank you so much for your reply. I'll try it.