# How to compute hessian
**URL:** https://discourse.julialang.org/t/how-to-compute-hessian/28012
**Category:** Machine Learning
**Created:** [August 26, 2019, 9:11pm UTC](https://discourse.julialang.org/t/how-to-compute-hessian/28012 "2019-08-26T21:11:33Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@stochastic\_guy](https://discourse.julialang.org/u/stochastic_guy)
#### Post date: [August 26, 2019, 9:11pm UTC](https://discourse.julialang.org/t/how-to-compute-hessian/28012/1 "2019-08-26T21:11:33Z")
**New to Flux!**
I want to compute the gradient and hessian for this loss function.
```julia
loss(x,y) = -sum(y.*log.(model(x)) .- (1 .- y).*log.(1 .- model(x))) * 1 // size(y, 2)
```
where
```julia
model = Flux.Dense(in,out,σ)
```
And how do you access the final values for hessain and gradient once the training is over
---
### Author:  [@baggepinnen](https://discourse.julialang.org/u/baggepinnen)
#### Post date: [August 26, 2019, 11:14pm UTC](https://discourse.julialang.org/t/how-to-compute-hessian/28012/2 "2019-08-26T23:14:08Z")
> [@\[Flux\] Issue while computing Hessian MethodError: objects of type Tracker.Grads are not callable](https://discourse.julialang.org/t/flux-issue-while-computing-hessian-methoderror-objects-of-type-tracker-grads-are-not-callable/27980):
>
> 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