Expected all tensors to be on the same device, but found at least two devices

    x = x + kp_x_ofst
    y = y + kp_y_ofst
    x = torch.reshape(x, [-1])  
    y = torch.reshape(y, [-1])
    
    x = x.to('cpu')
    y = y.to('cpu')
 
    x0 = torch.floor(x).to(torch.int32)
    x1 = x0 + 1
    y0 = torch.floor(y).to(torch.int32)
    y1 = y0 + 1
    # device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    x0 = torch.clamp(x0, zero, max_x)
    x1 = torch.clamp(x1, zero, max_x)
    y0 = torch.clamp(y0, zero, max_y)
    y1 = torch.clamp(y1, zero, max_y)