'trainingOptions' without 'trainNetwork' in deep learning

Question

feynman feynman 2022-12-3

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1869952-trainingoptions-without-trainnetwork-in-deep-learning

编辑： Walter Roberson 2022-12-3

采纳的回答： Walter Roberson

在 MATLAB Online 中打开

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'?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Walter Roberson 2022-12-3

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1869952-trainingoptions-without-trainnetwork-in-deep-learning#answer_1118982

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
显示无隐藏无

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'?