I want to take a gradient of NN but get the error MethodError: no method matching extract_gradient!(::Type{ForwardDiff.Tag{Chain{Tuple{Dense{typeof(relu),Array{Float32,2},Array{Float32,1}},Dense{typeof(identity),Array{Float32,2},Array{Float32,1}}}},Int64}}, ::Array{Array{ForwardDiff.Dual{ForwardDif…

Gradient of NN with respect to inputs

Sunny January 8, 2021, 1:21pm 2

Currently, I’m using jacobian instead of gradient because of a vector output, and it works

Topic		Replies	Views
ForwardDiff failing on simple polynomial New to Julia	1	963	September 28, 2017
Gradient of Neural Network wrapper can't be taken New to Julia differentiation	0	303	January 8, 2021
Types and gradients, including Forward.gradient General Usage	20	5588	December 20, 2016
ForwardDiff.gradient of function with nested functions calls General Usage question , package	2	838	September 21, 2018
How to get the gradient of NN wr to its input? Machine Learning flux	6	988	November 15, 2019