Hi ,
I understand that you want to define a LSTM with required number of features.
You can achieve this by using the “sequenceInputLayer” function and passing an input layer of the size that corresponds to the number of features in your data. In this case it is 3.
Refer to the below example code for better understanding.
numFeatures = 12;
numHiddenUnits = 100;
numClasses = 9;
layers = [ ...
sequenceInputLayer(numFeatures)
lstmLayer(numHiddenUnits,OutputMode="sequence")
fullyConnectedLayer(numClasses)
softmaxLayer];
Refer to the following documentation for more understanding of the “sequenceInputLayer” function and relevant code examples.
Hope it helps!
