pyGAT icon indicating copy to clipboard operation
pyGAT copied to clipboard

Published 20 hours ago • verified publisher icon Diego999

Running Error.

Open Sean0719 opened this issue 4 years ago • 1 comments

Hi,

When I ran this code. The following error appears " attention = torch.where(adj > 0, e, zero_vec) File "/home/sean/anaconda3/lib/python3.8/site-packages/torch/tensor.py", line 28, in wrapped return f(*args, **kwargs) RuntimeError: Could not run 'aten::gt.Scalar' with arguments from the 'SparseCUDATensorId' backend. 'aten::gt.Scalar' is only available for these backends: [CPUTensorId, CUDATensorId, QuantizedCPUTensorId, VariableTensorId]. " I did not know what happen? Could you please give some suggestions? Does my pytorch version is not correct? Thanks.

Sean0719 avatar Apr 28 '20 12:04 Sean0719

You need to use a sparse version GAT since your input is sparse.

DayChan avatar May 02 '20 00:05 DayChan