MATLAB Answers

training deep network accuary goes to 0 ?

1 view (last 30 days)
michael scheinfeild
michael scheinfeild on 9 Jun 2018
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');

  0 Comments

Sign in to comment.

Answers (0)

Products

Community Treasure Hunt

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

Start Hunting!