02_classsification_in_pytorch 9:54:31

[crice6719]

When trying to make predictions and print untrained preds, im getting a mat1 and ma2 must have same dtype error. I have created all the tensors of the float dtype so im not sure what might be causing this error. Any help would be greatly appreciated.

Link to the code

[tonyhaya]

Try to tranpose one of matrix torch.transpose(), https://pytorch.org/docs/stable/generated/torch.transpose.html

[mrdbourke]

Hi @crice6719,

The default datatype in PyTorch for models/data is torch.float32, however, I see you're using torch.float64.

Have you tried using torch.float32?

That may help (as I think the error comes from your model rather than your data).

In essence, it looks like your data is torch.float64 but your model will be torch.float32 (by default).