Is there an efficient way to compute the Hessian of a NN?

[stochastic_guy]

Did you have any luck @HenriDeh ? I’m facing similar issues.

[Flux] Issue while computing Hessian MethodError: objects of type Tracker.Grads are not callable

I’m new to Flux and I’m trying to compute the hessian. Here’s the code: grad = Flux.gradient(() -> loss(x, y), Flux.params(model)) hess = Flux.gradient(grad, Flux.params(model)) But when running the line to compute hessian, it’s throwing the following error MethodError: objects of type Tracker.Grads are not callable