Closed hongym7 closed 1 year ago
hi, I found the same problem.
you can edit the code like this:
with torch.no_grad(): results=testing(model,test_loader)
thank you very much. I have solved the problem.
------------------ 原始邮件 ------------------ 发件人: "manigalati/usad" @.>; 发送时间: 2021年11月19日(星期五) 上午10:15 @.>; @.**@.>; 主题: Re: [manigalati/usad] RuntimeError: CUDA out of memory. (#6)
hi, I found the same problem. you can edit the code like this: with torch.no_grad(): results=testing(model,test_loader)
— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.
I run this USAD.ipynb in jupyter-notebook.
train is ok. test is error. error message is below.
RuntimeError: CUDA out of memory. Tried to allocate 38.00 MiB (GPU 0; 10.76 GiB total capacity; 8.95 GiB already allocated; 17.06 MiB free; 9.61 GiB reserved in total by PyTorch)
=================================
How should I change the Parameter to solve this problem?
my gpu is GPU 0: GeForce RTX 2080 Ti, GPU 1: GeForce RTX 2080 Ti
Thank you.