Hello,
I am trying to build simple network which will recognize gender from voice. I have many records. I read them in DataStore but I cant get them in sequenceInputLayer. I tried everything. I know that my Neural network will maybe not work because of layers, but I only want to strat it and than I will make it accurate. Every record is longer than 6000 samples.
I gives me this error:
Error using trainNetwork (line 183)Invalid training data. Responses must be nonempty.Error in Program2 (line 31)net = trainNetwork(audioTrain,layers, options)
clc;close all;clear all;net = networkaudio = audioDatastore(fullfile('E:\Projekt\M or F'), ... 'IncludeSubfolders',true, ... 'FileExtension', '.wav', ... 'LabelSource','foldernames');labelCount = countEachLabel(audio)numTrainFiles = 1000;[audioTrain,audioValidation] = splitEachLabel(audio,numTrainFiles,'randomize');layers = [ ... sequenceInputLayer(6000) fullyConnectedLayer(10) softmaxLayer classificationLayer];options = trainingOptions("adam", ... "MaxEpochs",4, ... "MiniBatchSize",256, ... "Plots","training-progress", ... "Verbose",false, ... "Shuffle","every-epoch", ... "LearnRateSchedule","piecewise", ... "LearnRateDropFactor",0.1, ... "LearnRateDropPeriod",1, ... 'ValidationFrequency',100);net = trainNetwork(audioTrain,layers, options)
Best Answer