Second order derivatives fail on some (simple) functions

autograd
1

I’m sorry, about the poor subject, but I don’t know how to describe this better. I’m trying to compute some second order derivatives.

If I do this:

import torch as tc
x = tc.tensor(0.0, requires_grad=True)
loss = x**2
g = tc.autograd.grad(loss, x, create_graph=True)[0]
g2 = tc.autograd.grad(g, x)[0]

It runs fine. Yay!

It also works well with, say, a sine:

import torch as tc
x = tc.tensor(0.0, requires_grad=True)
loss = tc.sin(x)
g = tc.autograd.grad(loss, x, create_graph=True)[0]
g2 = tc.autograd.grad(g, x)[0]

Yay!

But for some other functions this fails. For example:

import torch as tc
x = tc.tensor(0.0, requires_grad=True)
loss = x
g = tc.autograd.grad(loss, x, create_graph=True)[0]
g2 = tc.autograd.grad(g, x)[0]

Fails with:

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

It also doesn’t work for:

import torch as tc
x = tc.tensor(0.0, requires_grad=True)
loss = x + 1
g = tc.autograd.grad(loss, x, create_graph=True)[0]
g2 = tc.autograd.grad(g, x)[0]

Any ideas?

2

Hey,

Please follow this forums post for some discussion on this. You can maybe try putting follow up questions there itself to keep it all at one place :slight_smile: