get matlab nural network parameter after training

11 visualizaciones (últimos 30 días)
mehdi
mehdi el 28 de Jul. de 2013
Respondida: Chika Maduabuchi el 13 de Oct. de 2021
hi i use neural network of matlab for classification. i want to know how can i store network parameter(such as epoches,time,mse,...)in a matrix after training? thanks alot

Respuesta aceptada

Greg Heath
Greg Heath el 30 de Jul. de 2013
The objects net and tr contain all of the parameters needed for training and evaluation The command
net = net
leads to recovering all of the pretraining parameters.
The command
tr = tr
leads to recovering all of the posttraining parameters and results.
Thank you for formally accepting my answer
Greg

Más respuestas (2)

Shashank Prasanna
Shashank Prasanna el 28 de Jul. de 2013
Everything you want is usually within the net object. Here is an example:
[x,t] = simplefit_dataset;
net = fitnet(10)
net = train(net,x,t);
net.trainParam
You can access epochs for example as follws:
net.trainParam.epochs

Chika Maduabuchi
Chika Maduabuchi el 13 de Oct. de 2021
Please, how do I train and store a set of parameters (weights) for my neural network?

Categorías

Más información sobre Deep Learning Toolbox en Help Center y File Exchange.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by