CODEWITHSUNDEEP
c#machine-learning
woofwoof
woofwoof

Reputation: 317

Why am I getting a OutofRangeException when running BackPropagation with Accord.NET?

I am messing with the different deep learning algorithms in Accord.NET. I decided to do this with spectra data I had lying around. I PCA transform the data so that it is reduced to 10 data points, using Accord's statistics toolbox. then follow the tutorial to the letter:

// Setup the deep belief network and initialize with random weights.
        DeepBeliefNetwork network = new DeepBeliefNetwork(transformedInputs.First().Length, 10, 10);
        new GaussianWeights(network, 0.1).Randomize();
        network.UpdateVisibleWeights();

        // Setup the learning algorithm.
        DeepBeliefNetworkLearning teacher = new DeepBeliefNetworkLearning(network)
        {
            Algorithm = (h, v, i) => new ContrastiveDivergenceLearning(h, v)
            {
                LearningRate = 0.1,
                Momentum = 0.5,
                Decay = 0.001,
            }
        };

        // Setup batches of input for learning.
        int batchCount = Math.Max(1, transformedInputs.Length / 100);
        // Create mini-batches to speed learning.
        int[] groups = Accord.Statistics.Tools.RandomGroups(transformedInputs.Length, batchCount);
        double[][][] batches = transformedInputs.Subgroups(groups);
        // Learning data for the specified layer.
        double[][][] layerData;

        // Unsupervised learning on each hidden layer, except for the output layer.
        for (int layerIndex = 0; layerIndex < network.Machines.Count - 1; layerIndex++)
        {
            teacher.LayerIndex = layerIndex;
            layerData = teacher.GetLayerInput(batches);
            for (int i = 0; i < 200; i++)
            {
                double error = teacher.RunEpoch(layerData) / transformedInputs.Length;
                if (i % 10 == 0)
                {
                    Console.WriteLine(i + ", Error = " + error);
                }
            }
        }

        // Supervised learning on entire network, to provide output classification.
        var teacher2 = new BackPropagationLearning(network)
        {
            LearningRate = 0.1,
            Momentum = 0.5
        };


        // Run supervised learning.
        for (int i = 0; i < 500; i++)
        {
            double error = teacher2.RunEpoch(transformedInputs, output: outputs);
            if (i % 10 == 0)
            {
                Console.WriteLine(i + ", Error = " + error);
            }
        }

I checked the inputted data and it is in the correct double[][] format fr both inputs and outputs. I also checked the original app:https://github.com/primaryobjects/deep-learning And that worked perfectly, so I am struggling to see what simply changing the inputted data is messing up so much. Any help would be greatly appreciated. The error I am getting is:

An unhandled exception of type 'System.IndexOutOfRangeException' occurred in Accord.Neuro.dll

Additional information: Index was outside the bounds of the array.

Upvotes: 2

Views: 527

Answers (1)

woofwoof
woofwoof

Reputation: 317

And of course it was immediately after posting this question that I realized that my network would have to reflect the number of outputs, and that was set to 10. I am very sorry for disturbing this fantastic community.

Upvotes: 3

Related Questions