Hi, I am doing a machine learning using gradient descend # I have a set of data, called samples # I have two models: model1 and model2 global par = Flux.params(model1, model2) #wrap them in params gs = gradient(par) do global l1 = mean(Flux.mse(model(sample),true1)) for sample in sa…

In your do block, the returned value is the value of the last expression. In this case, you actually return the output of a call to println, which is nothing (and it has no gradient). The last line of the do block needs to be return allLoss, and it should work?

Problems relating to "gradient is nothing"

General Usage

gdalle October 29, 2024, 2:14pm 11

See also

Did this solve your issue?

1 Like

Topic		Replies	Views
Flux.jl: params() and gradient() ocnfusion Machine Learning	4	628	August 23, 2021
Flux.gradient returns dict of param and Nothing Machine Learning flux	3	744	September 22, 2021
Problem on model and gradient descend in Flux General Usage	18	167	October 27, 2024
Please help with the very simplest 4-line Autodiff example: Flux0.9 Machine Learning flux	1	422	January 12, 2020
How to obtain gradients from training a model New to Julia flux	1	185	September 6, 2023

Problems relating to "gradient is nothing"

Related topics