[mlpack-git] [mlpack] ANN Saving the network and reloading (#531)
Joseph Mariadassou
notifications at github.com
Wed Mar 2 14:33:25 EST 2016
I had the same result when used make_tuple rather than tie. I fixed it
though in my own fork:
http://github.com/theSundayProgrammer/mlpack
fork:mytweaks
SHA1: 540dd7c3b3a5f3857eed922d446bfeb5016dbcd9
Although it is for CNN not FNN, I guess a similar change for FNN should
work too
On Thu, Mar 3, 2016 at 3:29 AM, sudarshan <notifications at github.com> wrote:
> Thank you. I checked out pr/536 and linked the include directories and lib
> from there. I got rid off all the compiler error. However, I get a 100%
> classification error when I use std::make_tuple, but when I use std::tie I
> get 4.95916%. This is my funciton:
>
> auto BuildFFN(MatType& trainData, MatType& trainLabels, MatType& testData, MatType& testLabels, const size_t hiddenLayerSize)
> {
> // input layer
> ann::LinearLayer<> inputLayer(trainData.n_rows, hiddenLayerSize);
> ann::BiasLayer<> inputBiasLayer(hiddenLayerSize);
> ann::BaseLayer<PerformanceFunction> inputBaseLayer;
>
> // hidden layer
> ann::LinearLayer<> hiddenLayer1(hiddenLayerSize, trainLabels.n_rows);
> ann::BiasLayer<> hiddenBiasLayer1(trainLabels.n_rows);
> ann::BaseLayer<PerformanceFunction> outputLayer;
>
> // output layer
> OutputLayerType classOutputLayer;
>
> auto modules = std::tie(inputLayer, inputBiasLayer, inputBaseLayer, hiddenLayer1, hiddenBiasLayer1, outputLayer);
> ann::FFN<decltype(modules), decltype(classOutputLayer), ann::RandomInitialization, PerformanceFunctionType> net(modules, classOutputLayer);
>
> net.Train(trainData, trainLabels);
> arma::mat prediction;
> net.Predict(testData, prediction);
>
> double classificationError;
> for (size_t i = 0; i < testData.n_cols; i++)
> {
> if (arma::sum(arma::sum(arma::abs(prediction.col(i) - testLabels.col(i)))) != 0)
> {
> classificationError++;
> }
> }
>
> std::cout << "Classification Error = " << (double(classificationError) / testData.n_cols) * 100 << "%" << std::endl;
>
> return net;
> }
>
> —
> Reply to this email directly or view it on GitHub
> <https://github.com/mlpack/mlpack/issues/531#issuecomment-191313956>.
>
--
Joseph Chakravarti Mariadassou
http://thesundayprogrammer.com
---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/issues/531#issuecomment-191389288
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160302/92e01aed/attachment.html>
More information about the mlpack-git
mailing list