This problem is obviously that the parameter types in the network do not agree;
modification:
add in front:
torch.set_default_tensor_type(torch.DoubleTensor)
Or, add before running the network:
net = net.double()
This problem is obviously that the parameter types in the network do not agree;
modification:
add in front:
torch.set_default_tensor_type(torch.DoubleTensor)
Or, add before running the network:
net = net.double()