How to set requires_grad = false in C++?

3

Hi Oktai15!

Thank you for your reply!

If I understood correctly, the NoGradGuard should, in essence, emulate the behaviour of requires_grad=false, correct?

If so, no parameters should change if I have the following, right? I.e., I should see the same bias before and after?

std::cout << "Biases before:\n" << policy->affine2->bias.data() << std::endl;

{
   torch::NoGradGuard no_grad;
   loss.backward();
   optimizer.step();
}

std::cout << "Biases after:\n" << policy->affine2->bias.data() << std::endl;

It turns out it still changed the biases, do you know why?