Gradient of input and model parameters

autograd
1

Hello,

I have a question regarding training a model’s parameters when the forward function include a gradient wrt to the input. Instead of showing all the code (where I have trouble with the backward-function), I can boil it down to this small (and silly) example (and when I can solve this problem I think it will translate to my code):

import torch as th
import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):

def __init__(self):
    super().__init__()
    self.l1 = nn.Linear(5, 2)

def forward(self, x):
    x_ = self.l1(x)
    x_ = (x_ ** 2).sum(1)
    return th.autograd.grad(x_, x, grad_outputs=th.ones_like(x_))[0]

m = Model()
m.train()
x = th.randn(10, 5).requires_grad_(True)
y = m(x)

loss = F.mse_loss(y, x)
params = m.parameters()
for p in params:
print(th.autograd.grad(loss, p, retain_graph=True)[0])

Here I cannot compute the gradient in the for-loop. How can I solve this?
Thanks in advance!!

2

Hi Saizor!

In the call to autograd.grad() in Model.forward() you need to use
create_graph = True.

(This is the same issue as the second question in the earlier thread you
posted. Or was that thread from Josue?)

Best.

K. Frank

3

Oh, thanks!

That must be someone else. Sorry, I did not find that thread!

Once again, thanks!

Best!