(deep learning)how to get probability output of softmax in this code?
9 views (last 30 days)
Show older comments
Yeon Hwee Bae
on 21 Sep 2020
Answered: Yeon Hwee Bae
on 22 Sep 2020
%%
[XTrain,YTrain] = japaneseVowelsTrainData;
XTrain(1:5)
%%
figure
plot(XTrain{1}')
xlabel("Time Step")
title("Training Observation 1")
numFeatures = size(XTrain{1},1);
legend("Feature " + string(1:numFeatures),'Location','northeastoutside')
%%
numObservations = numel(XTrain);
for i=1:numObservations
sequence = XTrain{i};
sequenceLengths(i) = size(sequence,2);
end
%%
[sequenceLengths,idx] = sort(sequenceLengths);
XTrain = XTrain(idx);
YTrain = YTrain(idx);
%%
figure
bar(sequenceLengths)
ylim([0 30])
xlabel("Sequence")
ylabel("Length")
title("Sorted Data")
%%
miniBatchSize = 27;
%%
inputSize = 12;
numHiddenUnits = 100;
numClasses = 9;
layers = [ ...
sequenceInputLayer(inputSize)
bilstmLayer(numHiddenUnits,'OutputMode','last')
fullyConnectedLayer(numClasses)
softmaxLayer
classificationLayer]
%%
maxEpochs = 100;
miniBatchSize = 27;
options = trainingOptions('adam', ...
'ExecutionEnvironment','cpu', ...
'GradientThreshold',1, ...
'MaxEpochs',maxEpochs, ...
'MiniBatchSize',miniBatchSize, ...
'SequenceLength','longest', ...
'Shuffle','never', ...
'Verbose',0, ...
'Plots','training-progress');
%%
net = trainNetwork(XTrain,YTrain,layers,options);
%%
[XTest,YTest] = japaneseVowelsTestData;
XTest(1:3)
%%
numObservationsTest = numel(XTest);
for i=1:numObservationsTest
sequence = XTest{i};
sequenceLengthsTest(i) = size(sequence,2);
end
[sequenceLengthsTest,idx] = sort(sequenceLengthsTest);
XTest = XTest(idx);
YTest = YTest(idx);
%%
miniBatchSize = 27;
YPred = classify(net,XTest, ...
'MiniBatchSize',miniBatchSize, ...
'SequenceLength','longest');
%%
acc = sum(YPred == YTest)./numel(YTest)
this is mathworks example code for sequence classification.
'Ypred' shows me the predicted classes
but I want to know the result after softmax, before prediction, the probablity.
how to know?
0 Comments
Accepted Answer
More Answers (0)
See Also
Categories
Find more on Image Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!