Inverse not implemented for type Variable

1

Hey guys,

I’ve been trying to play around with some gradients and came across an error while running this command:

return torch.inverse(torch.mm(x, x.t()))

This gave me the error:
TypeError: Type Variable doesn’t implement stateless method inverse

Is there an issue with my syntax, or is the inverse not implemented? Thanks!

Abhimanyu

2

torch.inverse takes tensor as an argument not Variable. You can get tensor out of a Variable using .data

1 Like
3

Thanks! I will try it out, however I need it to be differentiable. Will converting it to a tensor preserve the gradients?

4

Hey, I tried your suggestion - doesn’t work. The .data call is:
return torch.inverse(torch.mm(x, x.t()).data)

And I get the error:
AttributeError: 'FloatTensor' object has no attribute 'data'

5

The gradient of the inverse is not implemented, and apparently won’t be implemented in the nearby future, see https://github.com/pytorch/pytorch/issues/440

1 Like
6

That’s what the error was suggesting but apparently torch.mm returns a tensor and not a variable.
I don’t know why are you getting an error in the first place cuz I tried following code and it didn’t give any error:

mat1 = torch.randn(3, 3)
torch.inverse(torch.mm(mat1, mat1.t()))

7

@Rinku_Jadhav2014 in his code snippet, x is a Variable

8

Thanks for the link @fmassa! In my case, all eigenvalues of the variable are going to be <1 without exception, so I’ll just approximate the inverse with a power series I think.