3.2.1 RuntimeError: expected scalar type Double but found Float
lileidev opened this issue · comments
Larry commented
It reports "expected scalar type Double but found Float" with torch.mm in chapter 3.2.1.
Fixed by add "to (torch.float32)" as bellow:
features = torch.from_numpy(np.random.normal(0, 1, (num_examples, num_inputs))).to(torch.float32)