czkkkkkk
czkkkkkk
The achieved accuracy is different from DGL. Why is that?
@ali6947 Thanks for the contribution. We will discuss how to proceed for this PR.
Hi @sumenties, Currently DGL does not officially support CUDA 12.0 as Pytorch does not support it. We will support it as soon as Pytorch offers support on it.
> Suppose I don't wish to use GPU (even CPU would be sufficient for me) would DGL still require CUDA? I'm using DeepChem and some of its functions require DGL....
How do you call the `copy_to`? For the CPU DGL version, a DGLGraph cannot be copied to GPU.
The error occurs may because you are trying to call DGL functions on GPU Pytorch tensors. Could you check whether all the tensors you used are on CPU?
For example, you can avoid calling `.to('cuda')` for all tensors.