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.gradient returns dict of param and Nothing Machine Learning flux	3	766	September 22, 2021
Gradient not being computed when training NN using Flux Machine Learning question , flux , sciml	3	110	January 30, 2025
Computing Flux.gradient change the model Machine Learning	10	1373	January 31, 2021
Params not getting updated during training New to Julia flux	25	1739	October 11, 2020
Problem on model and gradient descend in Flux General Usage	18	207	October 27, 2024

Problems relating to "gradient is nothing"

Related topics