search

iMoonLab / PVRNet

PVRNet: Point-View Relation Neural Network for 3D Shape Recognition (AAAI 2019)
MIT License
44 stars 7 forks source link

torch.cuda.is_available() is False. #1

Closed longmalongma closed 4 years ago

longmalongma commented 4 years ago

Hello,Think your for your work,when I tried to run your code ,I met this problem.can you tell me how to solve this problem? raise RuntimeError('Attempting to deserialize object on a CUDA ' RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location='cpu' to map your storages to the CPU.

Hxyou commented 4 years ago

It seems you need a GPU and correctly configure it with CUDA, CUDNN.

longmalongma commented 4 years ago

Think your for your reply,I successfully make it ,I want to know your version about cuda,cudnn,pytorch,do you have code about this parper on the tensorflow?

Hxyou commented 4 years ago

The version of cuda and pytorch are listed in readme of our project. And the version of cudnn is 7.1.2. I am sorry to not have tensorflow code.

longmalongma commented 4 years ago

I want to know how I test my deep learning environment pytorch-gpu is useful？because I doubt my environment meet problem

------------------ Original ------------------ From: Haoxuanyou notifications@github.com Date: Tue,Jul 30,2019 4:14 PM To: iMoonLab/PVRNet PVRNet@noreply.github.com Cc: longma 1442342449@qq.com, Author author@noreply.github.com Subject: Re: [iMoonLab/PVRNet] torch.cuda.is_available() is False. (#1)

The version of cuda and pytorch are listed in readme of our project. And the version of cudnn is 7.1.2. I am sorry to not have tensorflow code.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.