'trainingOptions' without 'trainNetwork' in deep learning
1 Ansicht (letzte 30 Tage)
Ältere Kommentare anzeigen
feynman feynman
am 3 Dez. 2022
Bearbeitet: Walter Roberson
am 3 Dez. 2022
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 Kommentare
Akzeptierte Antwort
Walter Roberson
am 3 Dez. 2022
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 Kommentare
Walter Roberson
am 3 Dez. 2022
Bearbeitet: Walter Roberson
am 3 Dez. 2022
sgdmupdate and adamupdate do not have any named options.
Weitere Antworten (0)
Siehe auch
Kategorien
Mehr zu Image Data Workflows finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!