criterion = nn.MSELoss()
criterion(a, b)

This is dtype=torch.float for a and dtype=torch.int64 for b
So, both change to float

Similar Posts:

• [Solved] Pytoch nn.CrossEntropyLoss Error: RuntimeError: expected scalar type Long but found Float
• Keras.utils.to in keras_ Categorical method
• InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor ‘…
• Tensorflowcenter {typeerror} non hashable type: “numpy. Ndarray”
• After installing torch on Linux, an error is still reported: importerror: no module named torch
• Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same
• Error in loading pre training weight in torch. Load() in pytorch
• PyTorch UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` inst
• Examples of torch.NN.Functional.Relu() and torch.NN.Relu()
• [Solved] RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!