mlpack::ann::MiniBatchDiscrimination< InputDataType, OutputDataType > Class Template Reference

Implementation of the MiniBatchDiscrimination layer. More...

#include <minibatch_discrimination.hpp>

Public Member Functions
	MiniBatchDiscrimination ()
	Create the MiniBatchDiscrimination object.
	MiniBatchDiscrimination (const size_t inSize, const size_t outSize, const size_t features)
	Create the MiniBatchDiscrimination layer object using the specified number of units. More...
void	Reset ()
	Reset the layer parameter.
template<typename eT >
void	Forward (const arma::Mat< eT > &input, arma::Mat< eT > &output)
	Ordinary feed-forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...
template<typename eT >
void	Backward (const arma::Mat< eT > &, const arma::Mat< eT > &gy, arma::Mat< eT > &g)
	Ordinary feed-backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. More...
template<typename eT >
void	Gradient (const arma::Mat< eT > &input, const arma::Mat< eT > &, arma::Mat< eT > &gradient)
	Calculate the gradient using the output delta and the input activation. More...
OutputDataType const &	Parameters () const
	Get the parameters.
OutputDataType &	Parameters ()
	Modify the parameters.
InputDataType const &	InputParameter () const
	Get the input parameter.
InputDataType &	InputParameter ()
	Modify the input parameter.
OutputDataType const &	OutputParameter () const
	Get the output parameter.
OutputDataType &	OutputParameter ()
	Modify the output parameter.
OutputDataType const &	Delta () const
	Get the delta.
OutputDataType &	Delta ()
	Modify the delta.
OutputDataType const &	Gradient () const
	Get the gradient.
OutputDataType &	Gradient ()
	Modify the gradient.
size_t	InputShape () const
	Get the shape of the input.
template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::MiniBatchDiscrimination< InputDataType, OutputDataType >

Implementation of the MiniBatchDiscrimination layer.

MiniBatchDiscrimination is a layer of the discriminator that allows the discriminator to look at multiple data examples in combination and perform what is called as mini-batch discrimination. This helps prevent the collapse of the generator parameters to a setting where it emits the same point. This happens because normally a discriminator will process each example independently and there will be no mechanism to diversify the outputs of the generator.

For more information, see the following.

@article{Goodfellow2016,
  author  = {Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung,
             Alec Radford, Xi Chen},
  title   = {Improved Techniques for Training GANs},
  year    = {2016},
  url     = {https://arxiv.org/abs/1606.03498},
}

Template Parameters

InputDataType	Type of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputDataType	Type of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).

Constructor & Destructor Documentation

MiniBatchDiscrimination()

template<typename InputDataType , typename OutputDataType >

mlpack::ann::MiniBatchDiscrimination< InputDataType, OutputDataType >::MiniBatchDiscrimination	(	const size_t	inSize,
		const size_t	outSize,
		const size_t	features
	)

Create the MiniBatchDiscrimination layer object using the specified number of units.

Parameters

inSize	The number of input units.
outSize	The number of output units.
features	The number of features to compute for each dimension.

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType >

template<typename eT >

void mlpack::ann::MiniBatchDiscrimination< InputDataType, OutputDataType >::Backward	(	const arma::Mat< eT > &	,
		const arma::Mat< eT > &	gy,
		arma::Mat< eT > &	g
	)

Ordinary feed-backward pass of a neural network, calculating the function f(x) by propagating x backwards through f.

Using the results from the feed-forward pass.

Parameters

*	(input) The propagated input activation.
gy	The backpropagated error.
g	The calculated gradient.

Forward()

template<typename InputDataType , typename OutputDataType >

template<typename eT >

void mlpack::ann::MiniBatchDiscrimination< InputDataType, OutputDataType >::Forward	(	const arma::Mat< eT > &	input,
		arma::Mat< eT > &	output
	)

Ordinary feed-forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f.

Parameters

input	Input data used for evaluating the specified function.
output	Resulting output activation.

Gradient()

template<typename InputDataType , typename OutputDataType >

template<typename eT >

void mlpack::ann::MiniBatchDiscrimination< InputDataType, OutputDataType >::Gradient	(	const arma::Mat< eT > &	input,
		const arma::Mat< eT > &	,
		arma::Mat< eT > &	gradient
	)

Calculate the gradient using the output delta and the input activation.

Parameters

input	The input parameter used for calculating the gradient.
*	(error) The calculated error.
gradient	The calculated gradient.

---

The documentation for this class was generated from the following files:

• src/mlpack/methods/ann/layer/layer_types.hpp
• src/mlpack/methods/ann/layer/minibatch_discrimination.hpp
• src/mlpack/methods/ann/layer/minibatch_discrimination_impl.hpp