Aakash-kaushik

#include <mlpack/core.hpp>
#include <mlpack/core/data/split_data.hpp>
#include <mlpack/methods/ann/layer/layer.hpp>
#include <mlpack/methods/ann/ffn.hpp>
#include <ensmallen.hpp>  /* The numerical optimization library that mlpack uses */ 

using namespace mlpack;
using namespace mlpack::ann;

// Namespace for the armadillo library(linear algebra library).

Aakash-kaushik

arma::Row<size_t> getLabels(arma::mat predOut)
{
  arma::Row<size_t> predLabels(predOut.n_cols);
  for(arma::uword i = 0; i < predOut.n_cols; ++i)
  {
    predLabels(i) = predOut.col(i).index_mat() + 1;
  }
  return predLabels;
}

Aakash-kaushik

int main()
{
  constexpr double RATIO = 0.1; // ratio to divide the data in train and val set.
  constexpr int MAX_ITERATIONS = 0; // set to zero to allow infinite iterations.
  constexpr double STEP_SIZE = 1.2e-3;// step size for Adam optimizer.
  constexpr int BATCH_SIZE = 50;
  constexpr size_t EPOCH_I = 2;
  cout << "Reading data ..." << endl;
  mat tempDataset;
  data::Load("../data/mnist_train.csv", tempDataset, true);

Aakash-kaushik

constexpr double RATIO = 0.1; // ratio to divide the data in train and val set.
constexpr int MAX_ITERATIONS = 0; // set to zero to allow infinite iterations.
constexpr double STEP_SIZE = 1.2e-3;// step size for Adam optimizer.
constexpr int BATCH_SIZE = 50;
constexpr size_t EPOCH = 2;

mat tempDataset;
data::Load("train.csv", tempDataset, true);

mat tempTest;

Aakash-kaushik

mat dataset = tempDataset.submat(0, 1, tempDataset.n_rows - 1, tempDataset.n_cols - 1);

mat test = tempTest.submat(0, 1, tempTest.n_rows - 1, tempTest.n_cols - 1);

mat train, valid;
data::Split(dataset, train, valid, RATIO);

const mat trainX = train.submat(1, 0, train.n_rows - 1, train.n_cols - 1);
const mat validX = valid.submat(1, 0, valid.n_rows - 1, valid.n_cols - 1);
const mat testX = test.submat(1, 0, test.n_rows - 1, test.n_cols - 1);

Aakash-kaushik

FFN<NegativeLogLikelihood<>, RandomInitialization> model;

model.Add<Convolution<>>(1,  // Number of input activation maps.
                         6,  // Number of output activation maps.
                         5,  // Filter width.
                         5,  // Filter height.
                         1,  // Stride along width.
                         1,  // Stride along height.
                         0,  // Padding width.
                         0,  // Padding height.

Aakash-kaushik

ens::Adam optimizer(
   STEP_SIZE,  // Step size of the optimizer.
   BATCH_SIZE, // Batch size. Number of data points that are used in each iteration.
   0.9,        // Exponential decay rate for the first moment estimates.
   0.999, // Exponential decay rate for the weighted infinity norm estimates.
   1e-8,  // Value used to initialise the mean squared gradient parameter.
   MAX_ITERATIONS, // Max number of iterations.
   1e-8, // Tolerance.
   true);

Aakash-kaushik

mat predOut;
model.Predict(trainX, predOut);
arma::Row<size_t> predLabels = getLabels(predOut);
double trainAccuracy = arma::accu(predLabels == trainY) / ( double )trainY.n_elem * 100;
model.Predict(validX, predOut);
predLabels = getLabels(predOut);
double validAccuracy = arma::accu(predLabels == validY) / ( double )validY.n_elem * 100;
std::cout << "Accuracy: train = " << trainAccuracy << "%,"<< "\t valid = " << validAccuracy << "%" << std::endl;

mat testPredOut;

Aakash-kaushik

mlpack::data::Save("model.bin", "model", model, false);

Aakash-kaushik

FFN<NegativeLogLikelihood<>, RandomInitialization> friend_model;
mlpack::data::load("model.bin", "model", friend_model);