[mlpack-git] master: Refactor softmax layer for new network API. (5e395bd)
gitdub at big.cc.gt.atl.ga.us
gitdub at big.cc.gt.atl.ga.us
Tue Sep 1 03:58:12 EDT 2015
Repository : https://github.com/mlpack/mlpack
On branch : master
Link : https://github.com/mlpack/mlpack/compare/7b68ca3376ccf081e82146ef02710eedcd4f3aa8...236d5bcda2680cf2c5cae3ce6db7c342cad2842b
>---------------------------------------------------------------
commit 5e395bd1eb7426d0df8a24107ac0e85d354a05b4
Author: Marcus Edel <marcus.edel at fu-berlin.de>
Date: Sun Aug 30 17:24:38 2015 +0200
Refactor softmax layer for new network API.
>---------------------------------------------------------------
5e395bd1eb7426d0df8a24107ac0e85d354a05b4
src/mlpack/methods/ann/layer/softmax_layer.hpp | 172 +++++++------------------
1 file changed, 44 insertions(+), 128 deletions(-)
diff --git a/src/mlpack/methods/ann/layer/softmax_layer.hpp b/src/mlpack/methods/ann/layer/softmax_layer.hpp
index b47ec05..d2396c4 100644
--- a/src/mlpack/methods/ann/layer/softmax_layer.hpp
+++ b/src/mlpack/methods/ann/layer/softmax_layer.hpp
@@ -2,8 +2,7 @@
* @file softmax_layer.hpp
* @author Marcus Edel
*
- * Definition of the SoftmaxLayer class, which implements a standard softmax
- * network layer.
+ * Definition of the SoftmaxLayer class.
*/
#ifndef __MLPACK_METHODS_ANN_LAYER_SOFTMAX_LAYER_HPP
#define __MLPACK_METHODS_ANN_LAYER_SOFTMAX_LAYER_HPP
@@ -14,70 +13,25 @@ namespace mlpack {
namespace ann /** Artificial Neural Network. */ {
/**
- * An implementation of a standard softmax layer.
+ * Implementation of the softmax layer. The softmax loss layer computes the
+ * multinomial logistic loss of the softmax of its inputs.
*
- * @tparam DataType Type of data (arma::colvec, arma::mat arma::sp_mat or
- * arma::cube).
+ * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,
+ * arma::sp_mat or arma::cube).
+ * @tparam OutputDataType Type of the output data (arma::colvec, arma::mat,
+ * arma::sp_mat or arma::cube).
*/
-template <typename DataType = arma::colvec>
+template <
+ typename InputDataType = arma::mat,
+ typename OutputDataType = arma::mat
+>
class SoftmaxLayer
{
public:
/**
- * Create the SoftmaxLayer object using the specified number of neurons.
- *
- * @param layerSize The number of neurons.
- */
- SoftmaxLayer(const size_t layerSize) :
- inputActivations(arma::zeros<DataType>(layerSize)),
- delta(arma::zeros<DataType>(layerSize)),
- layerRows(layerSize),
- layerCols(1),
- layerSlices(1),
- outputMaps(1)
- {
- // Nothing to do here.
- }
-
- /**
- * Create 2-dimensional SoftmaxLayer object using the specified rows and
- * columns. In this case, DataType must be arma::mat or arma::sp_mat.
- *
- * @param layerRows The number of rows of neurons.
- * @param layerCols The number of columns of neurons.
- */
- SoftmaxLayer(const size_t layerRows, const size_t layerCols) :
- inputActivations(arma::zeros<DataType>(layerRows, layerCols)),
- delta(arma::zeros<DataType>(layerRows, layerCols)),
- layerRows(layerRows),
- layerCols(layerCols),
- layerSlices(1),
- outputMaps(1)
- {
- // Nothing to do here.
- }
-
- /**
- * Create n-dimensional SoftmaxLayer object using the specified rows and
- * columns and number of slices. In this case, DataType must be arma::cube.
- *
- * @param layerRows The number of rows of neurons.
- * @param layerCols The number of columns of neurons.
- * @param layerCols The number of slices of neurons.
- * @param layerCols The number of output maps.
+ * Create the SoftmaxLayer object.
*/
- SoftmaxLayer(const size_t layerRows,
- const size_t layerCols,
- const size_t layerSlices,
- const size_t outputMaps = 1) :
- inputActivations(arma::zeros<DataType>(layerRows, layerCols,
- layerSlices * outputMaps)),
- delta(arma::zeros<DataType>(layerRows, layerCols,
- layerSlices * outputMaps)),
- layerRows(layerRows),
- layerCols(layerCols),
- layerSlices(layerSlices),
- outputMaps(outputMaps)
+ SoftmaxLayer()
{
// Nothing to do here.
}
@@ -86,15 +40,15 @@ class SoftmaxLayer
* Ordinary feed forward pass of a neural network, evaluating the function
* f(x) by propagating the activity forward through f.
*
- * @param inputActivation Input data used for evaluating the specified
- * activity function.
- * @param outputActivation Data to store the resulting output activation.
+ * @param input Input data used for evaluating the specified function.
+ * @param output Resulting output activation.
*/
- void FeedForward(const DataType& inputActivation, DataType& outputActivation)
+ template<typename eT>
+ void Forward(const arma::Mat<eT>& input, arma::Mat<eT>& output)
{
- outputActivation = arma::trunc_exp(inputActivation -
- arma::repmat(arma::max(inputActivation), inputActivation.n_rows, 1));
- outputActivation /= arma::accu(outputActivation);
+ output = arma::trunc_exp(input -
+ arma::repmat(arma::max(input), input.n_rows, 1));
+ output /= arma::accu(output);
}
/**
@@ -102,80 +56,42 @@ class SoftmaxLayer
* f(x) by propagating x backwards trough f. Using the results from the feed
* forward pass.
*
- * @param inputActivation Input data used for calculating the function f(x).
- * @param error The backpropagated error.
- * @param delta The calculating delta using the partial derivative of the
- * error with respect to a weight.
+ * @param input The propagated input activation.
+ * @param gy The backpropagated error.
+ * @param g The calculated gradient.
*/
- void FeedBackward(const DataType& /* unused */,
- const DataType& error,
- DataType& delta)
+ template<typename eT>
+ void Backward(const arma::Mat<eT>& /* unused */,
+ const arma::Mat<eT>& gy,
+ arma::Mat<eT>& g)
{
- delta = error;
+ g = gy;
}
- //! Get the input activations.
- DataType& InputActivation() const { return inputActivations; }
- //! Modify the input activations.
- DataType& InputActivation() { return inputActivations; }
+ //! Get the input parameter.
+ InputDataType& InputParameter() const {return inputParameter; }
+ //! Modify the input parameter.
+ InputDataType& InputParameter() { return inputParameter; }
- //! Get the detla.
- DataType& Delta() const { return delta; }
- //! Modify the delta.
- DataType& Delta() { return delta; }
+ //! Get the output parameter.
+ OutputDataType& OutputParameter() const {return outputParameter; }
+ //! Modify the output parameter.
+ OutputDataType& OutputParameter() { return outputParameter; }
- //! Get input size.
- size_t InputSize() const { return layerRows; }
+ //! Get the delta.
+ InputDataType& Delta() const {return delta; }
//! Modify the delta.
- size_t& InputSize() { return layerRows; }
-
- //! Get output size.
- size_t OutputSize() const { return layerRows; }
- //! Modify the output size.
- size_t& OutputSize() { return layerRows; }
-
- //! Get the number of layer rows.
- size_t LayerRows() const { return layerRows; }
- //! Modify the number of layer rows.
- size_t& LayerRows() { return layerRows; }
-
- //! Get the number of layer columns.
- size_t LayerCols() const { return layerCols; }
- //! Modify the number of layer columns.
- size_t& LayerCols() { return layerCols; }
-
- //! Get the number of layer slices.
- size_t LayerSlices() const { return layerSlices; }
-
- //! Get the number of output maps.
- size_t OutputMaps() const { return outputMaps; }
-
- //! The the value of the deterministic parameter.
- bool Deterministic() const {return deterministic; }
- //! Modify the value of the deterministic parameter.
- bool& Deterministic() {return deterministic; }
+ InputDataType& Delta() { return delta; }
private:
- //! Locally-stored input activation object.
- DataType inputActivations;
-
//! Locally-stored delta object.
- DataType delta;
-
- //! Locally-stored number of layer rows.
- size_t layerRows;
-
- //! Locally-stored number of layer cols.
- size_t layerCols;
-
- //! Locally-stored number of layer slices.
- size_t layerSlices;
+ OutputDataType delta;
- //! Locally-stored number of output maps.
- size_t outputMaps;
+ //! Locally-stored input parameter object.
+ InputDataType inputParameter;
- //! Locally-stored deterministic parameter.
- bool deterministic;
+ //! Locally-stored output parameter object.
+ OutputDataType outputParameter;
}; // class SoftmaxLayer
}; // namespace ann
More information about the mlpack-git
mailing list