示例问题是实现'CUDA‘工具包。我能以某种方式修改代码并在我当前的笔记本电脑上运行吗?我已经使数据集足够小,这样它就不需要高计算量,并且可以在我的PC上运行!model = Net().to(device) # Net = A class inherited from torch.nn.Module
crit = t
我是PyTorch新手,错误地安装了CUDA10.2版的PyTorch。实际上,我的系统中没有CUDA。因此,当我编译我的程序时,我得到以下错误:
RuntimeError: Detected that PyTorch and torch_cluster were compiled with differentCUDA versions.PyTorch has CUDA version 10.2 and torch_cluster has CUDA v
torch.cuda.is_available() UserWarning: CUDA initialization: The NVIDIA driver on your systemDownload/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiledwith your version of the CUDA</