loading and training an existing network.

3 次查看（过去 30 天）
Mark Hubelbank
Mark Hubelbank 2024-10-7
编辑： Matt J 2024-10-8
I am trying define a network, then train it in multiple sessions. The problem is that I can't get the load or read of the network to work in the second session. The code is:
layers = [ ...
sequenceInputLayer(270)
bilstmLayer(numHiddenUnits,OutputMode="last")
fullyConnectedLayer(numClasses)
softmaxLayer
classificationLayer]
options = trainingOptions("adam", ...
InitialLearnRate=0.002,...
MaxEpochs=15, ...
Shuffle="never", ...
GradientThreshold=1, ...
Verbose=false, ...
ExecutionEnvironment="gpu", ...
Plots="training-progress");
clabels=categorical(labels);
numLables=numel(clabels)
load("savednet.mat","layers");
net = trainNetwork(data,clabels,layers,options);
save("savednet","net");
I have tried many variations of the load command and it always gives an error on the second argument:
Warning: Variable 'layers' not found.
Exactly what should that look like and then how should it be used as input to the trainNetwork routine?
  7 个评论
显示 5更早的评论
Mark Hubelbank
Mark Hubelbank 2024-10-7
移动：Walter Roberson 2024-10-7
Perhaps I don't understand how one can train in stages then. The idea is that the training will be continued in the second and subsequent sessions. Sort of a continuing transfer learning. The idea is that over time the network keeps improving. perhaps I should be using trainnet instead of trainnetwork. Then it would appear the call is:
load(filename,"net1","layers");
net=trainnet(data,clabels,net1,"crossentropy",options);
Is this the correct direction?
Walter Roberson
Walter Roberson 2024-10-7
Probably
net1 = trainnet(data,clabels,net1,"crossentropy",options);

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 2024-10-7
previous = load("savednet","net","layers");
net = trainNetwork(data,clabels,previous.net,options);
  1 个评论
Matt J
Matt J 2024-10-7
编辑：Matt J 2024-10-8
perhaps I should be using trainnet instead of trainnetwork.
It would be better, since trainnet is newer and has more flexibility. However, it won't make a difference as far as how to resume the training of a pre-existing network..

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

产品


版本

R2024b

Community Treasure Hunt

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

Start Hunting!

Translated by