Info

此问题已关闭。 请重新打开它进行编辑或回答。

training deep network accuary goes to 0 ?

1 次查看(过去 30 天)
hi i train lstm network and receive bad accuracy during the train what parameters i can change, layers to add
i have lstm network
numHiddenUnits = 100;
numClasses = 2;
layers = [ ...
sequenceInputLayer(inputSize)
lstmLayer(numHiddenUnits,'OutputMode','sequence')
fullyConnectedLayer(numClasses)
softmaxLayer
classificationLayer];
maxEpochs = 3;
miniBatchSize = 200;%100;
options = trainingOptions('adam', ...
'ExecutionEnvironment','cpu', ...
'GradientThreshold',1, ...
'MaxEpochs',maxEpochs, ...
'MiniBatchSize',miniBatchSize, ...
'SequenceLength','longest', ...
'Shuffle','never', ...
'Verbose',0, ...
'Plots','training-progress');

回答(0 个)

此问题已关闭。

标签

产品

Community Treasure Hunt

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

Start Hunting!

Translated by