Experiment Manager extremely slow
6 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Hello,
when I train a neural network it takes about 5-7 mins of computing time on my pc. When I compute it via experiment manager (bayesian optimization) it takes an hour to compute the network with the same stats... why such a huge difference?
Thanks in advance
Best
Réponse acceptée
Matt J
le 4 Mai 2022
Modifié(e) : Matt J
le 4 Mai 2022
But you understand, right, that when you use the Experiment Manager, your network is being retrained multiple times with different sets of hyperparameters? If as part of its search, the EM needs to test 10 sets of parameters, each requiring 5-10 min. of training, it makes sense that the whole exercise would be an hour long or more.
4 commentaires
晓龙 张
le 2 Sep 2022
That is not the reason. The speed is just very low even when single experiment is conducting!
Matt J
le 2 Sep 2022
But the training time will be different for every experiment, depending on the values of the hyperparameters. Have you really done a side-by-side comparison of the exact same training experiment, both with the same choice of hyperparameters?
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Pattern Recognition and Classification dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!