'trainingOptions' without 'trainNetwork' in deep learning

2 次查看（过去 30 天）
feynman feynman
feynman feynman 2022-12-3
编辑： Walter Roberson 2022-12-3
options = trainingOptions("sgdm", Plots="training-progress")
sets training options. This setting works when training is implemented via:
net = trainNetwork(layers,options)
But if training is implemented via the following instead:
for epoch=1:MaxEpochs
...
[net,velocity] = sgdmupdate(net,grad,velocity);
...
end
does 'trainingOptions' still take effect without 'trainNetwork'?

请先登录，再回答此问题。

采纳的回答

Walter Roberson
Walter Roberson 2022-12-3
No. trainNetwork knows to use the options because you pass the options in. sgdmupdate does not permit you to pass in options so there is no way for it to know which option to use.
The options are not stored as part of the network.
  2 个评论
feynman feynman
feynman feynman 2022-12-3
thanks so much. Then with 'sgdmupdate' or 'adamupdate', one can only specify training options by normal programming lines of code written by themselves rather than a structured function like 'trainingOptions'?
Walter Roberson
Walter Roberson 2022-12-3
编辑：Walter Roberson 2022-12-3
sgdmupdate and adamupdate do not have any named options.

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 Image 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