Experiment Manager extremely slow

4 次查看（过去 30 天）
ThomasP
ThomasP 2022-5-4
评论： Wendimu 2023-12-8
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
  2 个评论
晓龙 张
晓龙 张 2022-9-2
I have the same problem. The time is 2 times longer even worst! I wonder how to solve this problem?
Wendimu
Wendimu 2023-12-8
I am also having the same problem even with Shallow Neural Networks! What could be the cause of this?

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Matt J
Matt J 2022-5-4
编辑：Matt J 2022-5-4
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 个评论
显示 2更早的评论
晓龙 张
晓龙 张 2022-9-2
That is not the reason. The speed is just very low even when single experiment is conducting!
Matt J
Matt J 2022-9-2
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?

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by