after typing model.cuda() & data.cuda() in example.py, still wrong

[tomFoxxxx]

'''
exponent = torch.exp(-.5 * torch.sum((x - mu) * (x - mu) / var, 2, keepdim=True))

RuntimeError: expected device cpu and dtype Float but got device cuda:0 and dtype Float
'''
How could this program working rightly with GPU?

[tomFoxxxx]

solved!
When placing a class instance on the GPU, only properties and functions prefixed with self in init() will be placed on the GPU, and no other functions will be affected

[xiaobaoli15]

Hi，I have the same problem,can you share the detailed solution with me?thank you. @tomFoxxxx

[ldeecke]

Hi, does this issue still appear? If so, please post a minimal example for reproduction.