[mlpack-git] master: Add test for RMSprop. (b2d87c7)

[gitdub at mlpack.org]

Repository : https://github.com/mlpack/mlpack
On branch  : master
Link       : https://github.com/mlpack/mlpack/compare/f6dd2f7a9752a7db8ec284a938b3e84a13d0bfb2...6205f3e0b62b56452b2a4afc4da24fce5b21e72f

>---------------------------------------------------------------

commit b2d87c715ccde9575247ec9e5f0a190061411555
Author: marcus <marcus.edel at fu-berlin.de>
Date:   Tue Feb 16 21:55:23 2016 +0100

    Add test for RMSprop.


>---------------------------------------------------------------

b2d87c715ccde9575247ec9e5f0a190061411555
 src/mlpack/tests/rmsprop_test.cpp | 109 +++++++-------------------------------
 1 file changed, 18 insertions(+), 91 deletions(-)

diff --git a/src/mlpack/tests/rmsprop_test.cpp b/src/mlpack/tests/rmsprop_test.cpp
index 13c4bdd..bb556dc 100644
--- a/src/mlpack/tests/rmsprop_test.cpp
+++ b/src/mlpack/tests/rmsprop_test.cpp
@@ -2,112 +2,39 @@
  * @file rmsprop_test.cpp
  * @author Marcus Edel
  *
- * Tests the RMSProp optimizer on a couple test models.
+ * Tests the RMSProp optimizer.
  */
 #include <mlpack/core.hpp>
 
-#include <mlpack/methods/ann/activation_functions/logistic_function.hpp>
-
-#include <mlpack/methods/ann/init_rules/random_init.hpp>
-
-#include <mlpack/methods/ann/layer/bias_layer.hpp>
-#include <mlpack/methods/ann/layer/linear_layer.hpp>
-#include <mlpack/methods/ann/layer/base_layer.hpp>
-#include <mlpack/methods/ann/layer/one_hot_layer.hpp>
-
-#include <mlpack/methods/ann/trainer/trainer.hpp>
-#include <mlpack/methods/ann/ffn.hpp>
-#include <mlpack/methods/ann/performance_functions/mse_function.hpp>
-#include <mlpack/methods/ann/optimizer/rmsprop.hpp>
+#include <mlpack/core/optimizers/rmsprop/rmsprop.hpp>
+#include <mlpack/core/optimizers/lbfgs/test_functions.hpp>
+#include <mlpack/core/optimizers/sgd/test_function.hpp>
 
 #include <boost/test/unit_test.hpp>
 #include "old_boost_test_definitions.hpp"
 
+using namespace arma;
 using namespace mlpack;
-using namespace mlpack::ann;
+using namespace mlpack::optimization;
+using namespace mlpack::optimization::test;
 
-BOOST_AUTO_TEST_SUITE(RMSPropTest);
+BOOST_AUTO_TEST_SUITE(RMSpropTest);
 
 /**
- * Train and evaluate a vanilla network with the specified structure. Using the
- * iris data, the data set contains 3 classes. One class is linearly separable
- * from the other 2. The other two aren't linearly separable from each other.
+ * Tests the RMSprop optimizer using a simple test function.
  */
-BOOST_AUTO_TEST_CASE(SimpleRMSPropTestFunction)
+BOOST_AUTO_TEST_CASE(SimpleRMSpropTestFunction)
 {
-  const size_t hiddenLayerSize = 10;
-  const size_t maxEpochs = 300;
-
-  // Load the dataset.
-  arma::mat dataset, labels, labelsIdx;
-  data::Load("iris_train.csv", dataset, true);
-  data::Load("iris_train_labels.csv", labelsIdx, true);
-
-  // Create target matrix.
-  labels = arma::zeros<arma::mat>(labelsIdx.max() + 1, labelsIdx.n_cols);
-  for (size_t i = 0; i < labelsIdx.n_cols; i++)
-    labels(labelsIdx(0, i), i) = 1;
-
-  // Construct a feed forward network using the specified parameters.
-  RandomInitialization randInit(0.1, 0.1);
-
-  LinearLayer<RMSPROP, RandomInitialization> inputLayer(dataset.n_rows,
-      hiddenLayerSize, randInit);
-  BiasLayer<RMSPROP, RandomInitialization> inputBiasLayer(hiddenLayerSize,
-      1, randInit);
-  BaseLayer<LogisticFunction> inputBaseLayer;
-
-  LinearLayer<RMSPROP, RandomInitialization> hiddenLayer1(hiddenLayerSize,
-      labels.n_rows, randInit);
-  BiasLayer<RMSPROP, RandomInitialization> hiddenBiasLayer1(labels.n_rows,
-      1, randInit);
-  BaseLayer<LogisticFunction> outputLayer;
-
-  OneHotLayer classOutputLayer;
-
-  auto modules = std::tie(inputLayer, inputBiasLayer, inputBaseLayer,
-                          hiddenLayer1, hiddenBiasLayer1, outputLayer);
-
-  FFN<decltype(modules), OneHotLayer, MeanSquaredErrorFunction>
-      net(modules, classOutputLayer);
-
-  arma::mat prediction;
-  size_t error = 0;
-
-  // Evaluate the feed forward network.
-  for (size_t i = 0; i < dataset.n_cols; i++)
-  {
-    arma::mat input = dataset.unsafe_col(i);
-    net.Predict(input, prediction);
-
-    if (arma::sum(arma::sum(arma::abs(
-      prediction - labels.unsafe_col(i)))) == 0)
-      error++;
-  }
-
-  // Check if the selected model isn't already optimized.
-  double classificationError = 1 - double(error) / dataset.n_cols;
-  BOOST_REQUIRE_GE(classificationError, 0.09);
-
-  // Train the feed forward network.
-  Trainer<decltype(net)> trainer(net, maxEpochs, 1, 0.01, false);
-  trainer.Train(dataset, labels, dataset, labels);
-
-  // Evaluate the feed forward network.
-  error = 0;
-  for (size_t i = 0; i < dataset.n_cols; i++)
-  {
-    arma::mat input = dataset.unsafe_col(i);
-    net.Predict(input, prediction);
-
-    if (arma::sum(arma::sum(arma::abs(
-      prediction - labels.unsafe_col(i)))) == 0)
-      error++;
-  }
+  SGDTestFunction f;
+  RMSprop<SGDTestFunction> optimizer(f, 1e-3, 0.99, 1e-8, 5000000, 1e-9, true);
 
-  classificationError = 1 - double(error) / dataset.n_cols;
+  arma::mat coordinates = f.GetInitialPoint();
+  double result = optimizer.Optimize(coordinates);
 
-  BOOST_REQUIRE_LE(classificationError, 0.09);
+  BOOST_REQUIRE_CLOSE(result, -1.0, 0.05);
+  BOOST_REQUIRE_SMALL(coordinates[0], 1e-3);
+  BOOST_REQUIRE_SMALL(coordinates[1], 1e-3);
+  BOOST_REQUIRE_SMALL(coordinates[2], 1e-3);
 }
 
 BOOST_AUTO_TEST_SUITE_END();