\section{G\+AN$<$ Model, Initialization\+Rule\+Type, Noise, Policy\+Type $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1GAN}\index{G\+A\+N$<$ Model, Initialization\+Rule\+Type, Noise, Policy\+Type $>$@{G\+A\+N$<$ Model, Initialization\+Rule\+Type, Noise, Policy\+Type $>$}} The implementation of the standard \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} module. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ G\+AN} (Model generator, Model discriminator, Initialization\+Rule\+Type \&initialize\+Rule, Noise \&noise\+Function, const size\+\_\+t noise\+Dim, const size\+\_\+t batch\+Size, const size\+\_\+t generator\+Update\+Step, const size\+\_\+t pre\+Train\+Size, const double multiplier, const double clipping\+Parameter=0.\+01, const double lambda=10.\+0) \begin{DoxyCompactList}\small\item\em Constructor for \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} class. \end{DoxyCompactList}\item \textbf{ G\+AN} (const \textbf{ G\+AN} \&) \begin{DoxyCompactList}\small\item\em Copy constructor. \end{DoxyCompactList}\item \textbf{ G\+AN} (\textbf{ G\+AN} \&\&) \begin{DoxyCompactList}\small\item\em Move constructor. \end{DoxyCompactList}\item const Model \& \textbf{ Discriminator} () const \begin{DoxyCompactList}\small\item\em Return the discriminator of the \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN}. \end{DoxyCompactList}\item Model \& \textbf{ Discriminator} () \begin{DoxyCompactList}\small\item\em Modify the discriminator of the \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN}. \end{DoxyCompactList}\item {\footnotesize template$<$typename Policy = Policy\+Type$>$ }\\std\+::enable\+\_\+if$<$ std\+::is\+\_\+same$<$ Policy, \textbf{ Standard\+G\+AN} $>$\+::value$\vert$$\vert$std\+::is\+\_\+same$<$ Policy, \textbf{ D\+C\+G\+AN} $>$\+::value, double $>$\+::type \textbf{ Evaluate} (const arma\+::mat \¶meters, const size\+\_\+t i, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Evaluate function for the Standard \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} and \doxyref{D\+C\+G\+AN}{p.}{classmlpack_1_1ann_1_1DCGAN}. \end{DoxyCompactList}\item {\footnotesize template$<$typename Policy = Policy\+Type$>$ }\\std\+::enable\+\_\+if$<$ std\+::is\+\_\+same$<$ Policy, \textbf{ W\+G\+AN} $>$\+::value, double $>$\+::type \textbf{ Evaluate} (const arma\+::mat \¶meters, const size\+\_\+t i, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Evaluate function for the \doxyref{W\+G\+AN}{p.}{classmlpack_1_1ann_1_1WGAN}. \end{DoxyCompactList}\item {\footnotesize template$<$typename Policy = Policy\+Type$>$ }\\std\+::enable\+\_\+if$<$ std\+::is\+\_\+same$<$ Policy, \textbf{ W\+G\+A\+N\+GP} $>$\+::value, double $>$\+::type \textbf{ Evaluate} (const arma\+::mat \¶meters, const size\+\_\+t i, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Evaluate function for the W\+G\+A\+N-\/\+GP. \end{DoxyCompactList}\item {\footnotesize template$<$typename Grad\+Type , typename Policy = Policy\+Type$>$ }\\std\+::enable\+\_\+if$<$ std\+::is\+\_\+same$<$ Policy, \textbf{ Standard\+G\+AN} $>$\+::value$\vert$$\vert$std\+::is\+\_\+same$<$ Policy, \textbf{ D\+C\+G\+AN} $>$\+::value, double $>$\+::type \textbf{ Evaluate\+With\+Gradient} (const arma\+::mat \¶meters, const size\+\_\+t i, Grad\+Type \&gradient, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Evaluate\+With\+Gradient function for the Standard \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} and \doxyref{D\+C\+G\+AN}{p.}{classmlpack_1_1ann_1_1DCGAN}. \end{DoxyCompactList}\item {\footnotesize template$<$typename Grad\+Type , typename Policy = Policy\+Type$>$ }\\std\+::enable\+\_\+if$<$ std\+::is\+\_\+same$<$ Policy, \textbf{ W\+G\+AN} $>$\+::value, double $>$\+::type \textbf{ Evaluate\+With\+Gradient} (const arma\+::mat \¶meters, const size\+\_\+t i, Grad\+Type \&gradient, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Evaluate\+With\+Gradient function for the \doxyref{W\+G\+AN}{p.}{classmlpack_1_1ann_1_1WGAN}. \end{DoxyCompactList}\item {\footnotesize template$<$typename Grad\+Type , typename Policy = Policy\+Type$>$ }\\std\+::enable\+\_\+if$<$ std\+::is\+\_\+same$<$ Policy, \textbf{ W\+G\+A\+N\+GP} $>$\+::value, double $>$\+::type \textbf{ Evaluate\+With\+Gradient} (const arma\+::mat \¶meters, const size\+\_\+t i, Grad\+Type \&gradient, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Evaluate\+With\+Gradient function for the W\+G\+A\+N-\/\+GP. \end{DoxyCompactList}\item void \textbf{ Forward} (const arma\+::mat \&input) \begin{DoxyCompactList}\small\item\em This function does a forward pass through the \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} network. \end{DoxyCompactList}\item const Model \& \textbf{ Generator} () const \begin{DoxyCompactList}\small\item\em Return the generator of the \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN}. \end{DoxyCompactList}\item Model \& \textbf{ Generator} () \begin{DoxyCompactList}\small\item\em Modify the generator of the \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN}. \end{DoxyCompactList}\item {\footnotesize template$<$typename Policy = Policy\+Type$>$ }\\std\+::enable\+\_\+if$<$ std\+::is\+\_\+same$<$ Policy, \textbf{ Standard\+G\+AN} $>$\+::value$\vert$$\vert$std\+::is\+\_\+same$<$ Policy, \textbf{ D\+C\+G\+AN} $>$\+::value, void $>$\+::type \textbf{ Gradient} (const arma\+::mat \¶meters, const size\+\_\+t i, arma\+::mat \&gradient, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Gradient function for Standard \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} and \doxyref{D\+C\+G\+AN}{p.}{classmlpack_1_1ann_1_1DCGAN}. \end{DoxyCompactList}\item {\footnotesize template$<$typename Policy = Policy\+Type$>$ }\\std\+::enable\+\_\+if$<$ std\+::is\+\_\+same$<$ Policy, \textbf{ W\+G\+AN} $>$\+::value, void $>$\+::type \textbf{ Gradient} (const arma\+::mat \¶meters, const size\+\_\+t i, arma\+::mat \&gradient, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Gradient function for \doxyref{W\+G\+AN}{p.}{classmlpack_1_1ann_1_1WGAN}. \end{DoxyCompactList}\item {\footnotesize template$<$typename Policy = Policy\+Type$>$ }\\std\+::enable\+\_\+if$<$ std\+::is\+\_\+same$<$ Policy, \textbf{ W\+G\+A\+N\+GP} $>$\+::value, void $>$\+::type \textbf{ Gradient} (const arma\+::mat \¶meters, const size\+\_\+t i, arma\+::mat \&gradient, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Gradient function for W\+G\+A\+N-\/\+GP. \end{DoxyCompactList}\item size\+\_\+t \textbf{ Num\+Functions} () const \begin{DoxyCompactList}\small\item\em Return the number of separable functions (the number of predictor points). \end{DoxyCompactList}\item const arma\+::mat \& \textbf{ Parameters} () const \begin{DoxyCompactList}\small\item\em Return the parameters of the network. \end{DoxyCompactList}\item arma\+::mat \& \textbf{ Parameters} () \begin{DoxyCompactList}\small\item\em Modify the parameters of the network. \end{DoxyCompactList}\item void \textbf{ Predict} (arma\+::mat input, arma\+::mat \&output) \begin{DoxyCompactList}\small\item\em This function predicts the output of the network on the given input. \end{DoxyCompactList}\item const arma\+::mat \& \textbf{ Predictors} () const \begin{DoxyCompactList}\small\item\em Get the matrix of data points (predictors). \end{DoxyCompactList}\item arma\+::mat \& \textbf{ Predictors} () \begin{DoxyCompactList}\small\item\em Modify the matrix of data points (predictors). \end{DoxyCompactList}\item void \textbf{ Reset} () \item void \textbf{ Reset\+Data} (arma\+::mat train\+Data) \begin{DoxyCompactList}\small\item\em Initialize the generator, discriminator and weights of the model for training. \end{DoxyCompactList}\item const arma\+::mat \& \textbf{ Responses} () const \begin{DoxyCompactList}\small\item\em Get the matrix of responses to the input data points. \end{DoxyCompactList}\item arma\+::mat \& \textbf{ Responses} () \begin{DoxyCompactList}\small\item\em Modify the matrix of responses to the input data points. \end{DoxyCompactList}\item {\footnotesize template$<$typename Archive $>$ }\\void \textbf{ serialize} (Archive \&ar, const unsigned int) \begin{DoxyCompactList}\small\item\em Serialize the model. \end{DoxyCompactList}\item void \textbf{ Shuffle} () \begin{DoxyCompactList}\small\item\em Shuffle the order of function visitation. \end{DoxyCompactList}\item {\footnotesize template$<$typename Optimizer\+Type , typename... Callback\+Types$>$ }\\double \textbf{ Train} (arma\+::mat train\+Data, Optimizer\+Type \&Optimizer, Callback\+Types \&\&... callbacks) \begin{DoxyCompactList}\small\item\em Train function. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection{Detailed Description} \subsubsection*{template$<$typename Model, typename Initialization\+Rule\+Type, typename Noise, typename Policy\+Type = Standard\+G\+AN$>$\newline class mlpack\+::ann\+::\+G\+A\+N$<$ Model, Initialization\+Rule\+Type, Noise, Policy\+Type $>$} The implementation of the standard \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} module. Generative Adversarial Networks (G\+A\+Ns) are a class of artificial intelligence algorithms used in unsupervised machine learning, implemented by a system of two neural networks contesting with each other in a zero-\/sum game framework. This technique can generate photographs that look at least superficially authentic to human observers, having many realistic characteristics. G\+A\+Ns have been used in Text-\/to-\/\+Image Synthesis, Medical Drug Discovery, High Resolution Imagery Generation, Neural Machine Translation and so on. For more information, see the following paper\+: \begin{DoxyCode} @article\{Goodfellow14, author = \{Ian J. Goodfellow, Jean Pouget-Abadi, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville and Yoshua Bengio\}, title = \{Generative Adversarial Nets\}, year = \{2014\}, url = \{http:\textcolor{comment}{//arxiv.org/abs/1406.2661\},} eprint = \{1406.2661\}, \} \end{DoxyCode} \begin{DoxyTemplParams}{Template Parameters} {\em Model} & The class type of Generator and Discriminator. \\ \hline {\em Initialization\+Rule\+Type} & Type of Initializer. \\ \hline {\em Noise} & The noise function to use. \\ \hline {\em Policy\+Type} & The \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} variant to be used (\doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN}, \doxyref{D\+C\+G\+AN}{p.}{classmlpack_1_1ann_1_1DCGAN}, \doxyref{W\+G\+AN}{p.}{classmlpack_1_1ann_1_1WGAN} or \doxyref{W\+G\+A\+N\+GP}{p.}{classmlpack_1_1ann_1_1WGANGP}). \\ \hline \end{DoxyTemplParams} Definition at line 63 of file gan.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1GAN_afd4728e4b8193b03b9ee774b833d3508}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!G\+AN@{G\+AN}} \index{G\+AN@{G\+AN}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{G\+A\+N()\hspace{0.1cm}{\footnotesize\ttfamily [1/3]}} {\footnotesize\ttfamily \textbf{ G\+AN} (\begin{DoxyParamCaption}\item[{Model}]{generator, }\item[{Model}]{discriminator, }\item[{Initialization\+Rule\+Type \&}]{initialize\+Rule, }\item[{Noise \&}]{noise\+Function, }\item[{const size\+\_\+t}]{noise\+Dim, }\item[{const size\+\_\+t}]{batch\+Size, }\item[{const size\+\_\+t}]{generator\+Update\+Step, }\item[{const size\+\_\+t}]{pre\+Train\+Size, }\item[{const double}]{multiplier, }\item[{const double}]{clipping\+Parameter = {\ttfamily 0.01}, }\item[{const double}]{lambda = {\ttfamily 10.0} }\end{DoxyParamCaption})} Constructor for \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} class. \begin{DoxyParams}{Parameters} {\em generator} & Generator network. \\ \hline {\em discriminator} & Discriminator network. \\ \hline {\em initialize\+Rule} & Initialization rule to use for initializing parameters. \\ \hline {\em noise\+Function} & Function to be used for generating noise. \\ \hline {\em noise\+Dim} & Dimension of noise vector to be created. \\ \hline {\em batch\+Size} & Batch size to be used for training. \\ \hline {\em generator\+Update\+Step} & Number of steps to train Discriminator before updating Generator. \\ \hline {\em pre\+Train\+Size} & Number of pre-\/training steps of Discriminator. \\ \hline {\em multiplier} & Ratio of learning rate of Discriminator to the Generator. \\ \hline {\em clipping\+Parameter} & Weight range for enforcing Lipschitz constraint. \\ \hline {\em lambda} & Parameter for setting the gradient penalty. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a0c66c15a1fd7ab0ce0f579e20c838abb}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!G\+AN@{G\+AN}} \index{G\+AN@{G\+AN}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{G\+A\+N()\hspace{0.1cm}{\footnotesize\ttfamily [2/3]}} {\footnotesize\ttfamily \textbf{ G\+AN} (\begin{DoxyParamCaption}\item[{const \textbf{ G\+AN}$<$ Model, Initialization\+Rule\+Type, Noise, Policy\+Type $>$ \&}]{ }\end{DoxyParamCaption})} Copy constructor. \mbox{\label{classmlpack_1_1ann_1_1GAN_a0601671158b961d0b3f532beb0c070d7}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!G\+AN@{G\+AN}} \index{G\+AN@{G\+AN}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{G\+A\+N()\hspace{0.1cm}{\footnotesize\ttfamily [3/3]}} {\footnotesize\ttfamily \textbf{ G\+AN} (\begin{DoxyParamCaption}\item[{\textbf{ G\+AN}$<$ Model, Initialization\+Rule\+Type, Noise, Policy\+Type $>$ \&\&}]{ }\end{DoxyParamCaption})} Move constructor. \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1GAN_a81daab6e936bba0d45878d26df58aa9f}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Discriminator@{Discriminator}} \index{Discriminator@{Discriminator}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Discriminator()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const Model\& Discriminator (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Return the discriminator of the \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN}. Definition at line 312 of file gan.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1GAN_a52ce6e63f168b2f2a702b17f2225389a}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Discriminator@{Discriminator}} \index{Discriminator@{Discriminator}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Discriminator()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Model\& Discriminator (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the discriminator of the \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN}. Definition at line 314 of file gan.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1GAN_a1960af22a953da7d4280f8717f80102b}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Evaluate@{Evaluate}} \index{Evaluate@{Evaluate}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Evaluate()\hspace{0.1cm}{\footnotesize\ttfamily [1/3]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$std\+::is\+\_\+same$<$Policy, \textbf{ Standard\+G\+AN}$>$\+::value $\vert$$\vert$ std\+::is\+\_\+same$<$Policy, \textbf{ D\+C\+G\+AN}$>$\+::value, double$>$\+::type Evaluate (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{i, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Evaluate function for the Standard \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} and \doxyref{D\+C\+G\+AN}{p.}{classmlpack_1_1ann_1_1DCGAN}. This function gives the performance of the Standard \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} or \doxyref{D\+C\+G\+AN}{p.}{classmlpack_1_1ann_1_1DCGAN} on the current input. \begin{DoxyParams}{Parameters} {\em parameters} & The parameters of the network. \\ \hline {\em i} & Index of the current input. \\ \hline {\em batch\+Size} & Variable to store the present number of inputs. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a6e686598c5a781cc1b0903a0f24e54f3}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Evaluate@{Evaluate}} \index{Evaluate@{Evaluate}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Evaluate()\hspace{0.1cm}{\footnotesize\ttfamily [2/3]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$std\+::is\+\_\+same$<$Policy, \textbf{ W\+G\+AN}$>$\+::value, double$>$\+::type Evaluate (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{i, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Evaluate function for the \doxyref{W\+G\+AN}{p.}{classmlpack_1_1ann_1_1WGAN}. This function gives the performance of the \doxyref{W\+G\+AN}{p.}{classmlpack_1_1ann_1_1WGAN} on the current input. \begin{DoxyParams}{Parameters} {\em parameters} & The parameters of the network. \\ \hline {\em i} & Index of the current input. \\ \hline {\em batch\+Size} & Variable to store the present number of inputs. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_ab15c3bf890c114b50dab1dce9c0a0ae5}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Evaluate@{Evaluate}} \index{Evaluate@{Evaluate}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Evaluate()\hspace{0.1cm}{\footnotesize\ttfamily [3/3]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$std\+::is\+\_\+same$<$Policy, \textbf{ W\+G\+A\+N\+GP}$>$\+::value, double$>$\+::type Evaluate (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{i, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Evaluate function for the W\+G\+A\+N-\/\+GP. This function gives the performance of the W\+G\+A\+N-\/\+GP on the current input. \begin{DoxyParams}{Parameters} {\em parameters} & The parameters of the network. \\ \hline {\em i} & Index of the current input. \\ \hline {\em batch\+Size} & Variable to store the present number of inputs. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a8852fa0ac9f2147801776c5aff61f22c}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Evaluate\+With\+Gradient@{Evaluate\+With\+Gradient}} \index{Evaluate\+With\+Gradient@{Evaluate\+With\+Gradient}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Evaluate\+With\+Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [1/3]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$std\+::is\+\_\+same$<$Policy, \textbf{ Standard\+G\+AN}$>$\+::value $\vert$$\vert$ std\+::is\+\_\+same$<$Policy, \textbf{ D\+C\+G\+AN}$>$\+::value, double$>$\+::type Evaluate\+With\+Gradient (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{i, }\item[{Grad\+Type \&}]{gradient, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Evaluate\+With\+Gradient function for the Standard \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} and \doxyref{D\+C\+G\+AN}{p.}{classmlpack_1_1ann_1_1DCGAN}. This function gives the performance of the Standard \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} or \doxyref{D\+C\+G\+AN}{p.}{classmlpack_1_1ann_1_1DCGAN} on the current input, while updating Gradients. \begin{DoxyParams}{Parameters} {\em parameters} & The parameters of the network. \\ \hline {\em i} & Index of the current input. \\ \hline {\em gradient} & Variable to store the present gradient. \\ \hline {\em batch\+Size} & Variable to store the present number of inputs. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a5726150df7dbbde1aecf3d46cb155005}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Evaluate\+With\+Gradient@{Evaluate\+With\+Gradient}} \index{Evaluate\+With\+Gradient@{Evaluate\+With\+Gradient}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Evaluate\+With\+Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [2/3]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$std\+::is\+\_\+same$<$Policy, \textbf{ W\+G\+AN}$>$\+::value, double$>$\+::type Evaluate\+With\+Gradient (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{i, }\item[{Grad\+Type \&}]{gradient, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Evaluate\+With\+Gradient function for the \doxyref{W\+G\+AN}{p.}{classmlpack_1_1ann_1_1WGAN}. This function gives the performance of the \doxyref{W\+G\+AN}{p.}{classmlpack_1_1ann_1_1WGAN} on the current input, while updating Gradients. \begin{DoxyParams}{Parameters} {\em parameters} & The parameters of the network. \\ \hline {\em i} & Index of the current input. \\ \hline {\em gradient} & Variable to store the present gradient. \\ \hline {\em batch\+Size} & Variable to store the present number of inputs. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a41c7fcfc409e29d086df197d78c9b92d}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Evaluate\+With\+Gradient@{Evaluate\+With\+Gradient}} \index{Evaluate\+With\+Gradient@{Evaluate\+With\+Gradient}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Evaluate\+With\+Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [3/3]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$std\+::is\+\_\+same$<$Policy, \textbf{ W\+G\+A\+N\+GP}$>$\+::value, double$>$\+::type Evaluate\+With\+Gradient (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{i, }\item[{Grad\+Type \&}]{gradient, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Evaluate\+With\+Gradient function for the W\+G\+A\+N-\/\+GP. This function gives the performance of the W\+G\+A\+N-\/\+GP on the current input, while updating Gradients. \begin{DoxyParams}{Parameters} {\em parameters} & The parameters of the network. \\ \hline {\em i} & Index of the current input. \\ \hline {\em gradient} & Variable to store the present gradient. \\ \hline {\em batch\+Size} & Variable to store the present number of inputs. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a0f1a354ec201efe4ce96126802cf9a2f}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Forward()} {\footnotesize\ttfamily void Forward (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{input }\end{DoxyParamCaption})} This function does a forward pass through the \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} network. \begin{DoxyParams}{Parameters} {\em input} & Sampled noise. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a1b687745cb12ef7ef76449187dc50bb5}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Generator@{Generator}} \index{Generator@{Generator}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Generator()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const Model\& Generator (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Return the generator of the \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN}. Definition at line 308 of file gan.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1GAN_a8bf07503608839011670b808cdd17001}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Generator@{Generator}} \index{Generator@{Generator}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Generator()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Model\& Generator (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the generator of the \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN}. Definition at line 310 of file gan.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1GAN_a2e967aa7bd78aa8e5024899a44a303c9}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [1/3]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$std\+::is\+\_\+same$<$Policy, \textbf{ Standard\+G\+AN}$>$\+::value $\vert$$\vert$ std\+::is\+\_\+same$<$Policy, \textbf{ D\+C\+G\+AN}$>$\+::value, void$>$\+::type Gradient (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{i, }\item[{arma\+::mat \&}]{gradient, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Gradient function for Standard \doxyref{G\+AN}{p.}{classmlpack_1_1ann_1_1GAN} and \doxyref{D\+C\+G\+AN}{p.}{classmlpack_1_1ann_1_1DCGAN}. This function passes the gradient based on which network is being trained, i.\+e., Generator or Discriminator. \begin{DoxyParams}{Parameters} {\em parameters} & present parameters of the network. \\ \hline {\em i} & Index of the predictors. \\ \hline {\em gradient} & Variable to store the present gradient. \\ \hline {\em batch\+Size} & Variable to store the present number of inputs. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a3053059f0001ebb407739820357d050d}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [2/3]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$std\+::is\+\_\+same$<$Policy, \textbf{ W\+G\+AN}$>$\+::value, void$>$\+::type Gradient (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{i, }\item[{arma\+::mat \&}]{gradient, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Gradient function for \doxyref{W\+G\+AN}{p.}{classmlpack_1_1ann_1_1WGAN}. This function passes the gradient based on which network is being trained, i.\+e., Generator or Discriminator. \begin{DoxyParams}{Parameters} {\em parameters} & present parameters of the network. \\ \hline {\em i} & Index of the predictors. \\ \hline {\em gradient} & Variable to store the present gradient. \\ \hline {\em batch\+Size} & Variable to store the present number of inputs. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a488f9e118fd4fd3c25f29b81b839cf7a}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [3/3]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$std\+::is\+\_\+same$<$Policy, \textbf{ W\+G\+A\+N\+GP}$>$\+::value, void$>$\+::type Gradient (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{i, }\item[{arma\+::mat \&}]{gradient, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Gradient function for W\+G\+A\+N-\/\+GP. This function passes the gradient based on which network is being trained, i.\+e., Generator or Discriminator. \begin{DoxyParams}{Parameters} {\em parameters} & present parameters of the network. \\ \hline {\em i} & Index of the predictors. \\ \hline {\em gradient} & Variable to store the present gradient. \\ \hline {\em batch\+Size} & Variable to store the present number of inputs. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a1fa76af34a6e3ea927b307f0c318ee4b}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Num\+Functions@{Num\+Functions}} \index{Num\+Functions@{Num\+Functions}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Num\+Functions()} {\footnotesize\ttfamily size\+\_\+t Num\+Functions (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Return the number of separable functions (the number of predictor points). Definition at line 317 of file gan.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1GAN_aa68d74dc1e86e4352e00a3cab83a0e4a}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Parameters@{Parameters}} \index{Parameters@{Parameters}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Parameters()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const arma\+::mat\& Parameters (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Return the parameters of the network. Definition at line 303 of file gan.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1GAN_a043f0ccd62e6711a18e0d81047be9a0a}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Parameters@{Parameters}} \index{Parameters@{Parameters}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Parameters()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily arma\+::mat\& Parameters (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the parameters of the network. Definition at line 305 of file gan.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1GAN_a1c9a003262a7e893e46cf780ed5f359d}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Predict@{Predict}} \index{Predict@{Predict}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Predict()} {\footnotesize\ttfamily void Predict (\begin{DoxyParamCaption}\item[{arma\+::mat}]{input, }\item[{arma\+::mat \&}]{output }\end{DoxyParamCaption})} This function predicts the output of the network on the given input. \begin{DoxyParams}{Parameters} {\em input} & The input of the Generator network. \\ \hline {\em output} & Result of the Discriminator network. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_af63d9ce84ba796336c0abce63ff9be1c}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Predictors@{Predictors}} \index{Predictors@{Predictors}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Predictors()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const arma\+::mat\& Predictors (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the matrix of data points (predictors). Definition at line 325 of file gan.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1GAN_a5b2b9103f156a387b74164f143e63ce7}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Predictors@{Predictors}} \index{Predictors@{Predictors}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Predictors()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily arma\+::mat\& Predictors (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the matrix of data points (predictors). Definition at line 327 of file gan.\+hpp. References G\+A\+N$<$ Model, Initialization\+Rule\+Type, Noise, Policy\+Type $>$\+::serialize(). \mbox{\label{classmlpack_1_1ann_1_1GAN_a372de693ad40b3f42839c8ec6ac845f4}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Reset@{Reset}} \index{Reset@{Reset}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Reset()} {\footnotesize\ttfamily void Reset (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} \mbox{\label{classmlpack_1_1ann_1_1GAN_a935be322c1c9425a5ae7a0fe80421e83}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Reset\+Data@{Reset\+Data}} \index{Reset\+Data@{Reset\+Data}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Reset\+Data()} {\footnotesize\ttfamily void Reset\+Data (\begin{DoxyParamCaption}\item[{arma\+::mat}]{train\+Data }\end{DoxyParamCaption})} Initialize the generator, discriminator and weights of the model for training. This function won\textquotesingle{}t actually trigger training process. \begin{DoxyParams}{Parameters} {\em train\+Data} & The data points of real distribution. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1GAN_a5702d7dbe418472e341da9c8d8ff0e01}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Responses@{Responses}} \index{Responses@{Responses}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Responses()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const arma\+::mat\& Responses (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the matrix of responses to the input data points. Definition at line 320 of file gan.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1GAN_a94a56f6f545988833a4ae9906f8aa197}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Responses@{Responses}} \index{Responses@{Responses}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Responses()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily arma\+::mat\& Responses (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the matrix of responses to the input data points. Definition at line 322 of file gan.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1GAN_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the model. Referenced by G\+A\+N$<$ Model, Initialization\+Rule\+Type, Noise, Policy\+Type $>$\+::\+Predictors(). \mbox{\label{classmlpack_1_1ann_1_1GAN_a2697cc8b37d7bca7c055228382a9b208}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Shuffle@{Shuffle}} \index{Shuffle@{Shuffle}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Shuffle()} {\footnotesize\ttfamily void Shuffle (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Shuffle the order of function visitation. This may be called by the optimizer. \mbox{\label{classmlpack_1_1ann_1_1GAN_a4f7b5c4f299346d1fe308881a26696f0}} \index{mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}!Train@{Train}} \index{Train@{Train}!mlpack\+::ann\+::\+G\+AN@{mlpack\+::ann\+::\+G\+AN}} \subsubsection{Train()} {\footnotesize\ttfamily double Train (\begin{DoxyParamCaption}\item[{arma\+::mat}]{train\+Data, }\item[{Optimizer\+Type \&}]{Optimizer, }\item[{Callback\+Types \&\&...}]{callbacks }\end{DoxyParamCaption})} Train function. \begin{DoxyTemplParams}{Template Parameters} {\em Optimizer\+Type} & Type of optimizer to use to train the model. \\ \hline {\em Callback\+Types} & Types of Callback functions. \\ \hline \end{DoxyTemplParams} \begin{DoxyParams}{Parameters} {\em train\+Data} & The data points of real distribution. \\ \hline {\em optimizer} & Instantiated optimizer used to train the model. \\ \hline {\em callbacks} & Callback function for ensmallen optimizer {\ttfamily Optimizer\+Type}. See {\tt https\+://www.\+ensmallen.\+org/docs.\+html\#callback-\/documentation}. \\ \hline \end{DoxyParams} \begin{DoxyReturn}{Returns} The final objective of the trained model (NaN or Inf on error). \end{DoxyReturn} The documentation for this class was generated from the following file\+:\begin{DoxyCompactItemize} \item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/3.\+3.\+1/src/mlpack/methods/ann/gan/\textbf{ gan.\+hpp}\end{DoxyCompactItemize}