☰

神经网络图内的 if-then-else 的使用

tag-icon • tag-icon tikz-pgf
神经网络图内的 if-then-else 的使用

我想使用 if-then-else 语句来绘制 \vdots 而不是节点。在下图中：

\documentclass[border=1mm]{standalone}
\usepackage{amsmath}
\usepackage{tikz,pgfplots}
\usepackage{xifthen}
\pgfplotsset{compat=1.15}


\begin{document}
\pagestyle{empty}

\def\layersep{2.5cm}
\def\layersepp{5cm}

\begin{tikzpicture}[shorten >=1pt,->,draw=black!50, node distance=\layersep,]
    \tikzstyle{every pin edge}=[<-,shorten <=1pt]
    \tikzstyle{neuron}=[circle,fill=black!25,minimum size=17pt,inner sep=0pt]
    \tikzstyle{input neuron}=[neuron, fill=green!50];
    \tikzstyle{output neuron}=[neuron, fill=red!50];
    \tikzstyle{hidden neuron}=[neuron, fill=blue!50];
    \tikzstyle{annot} = [text width=4em, text centered]

    % Draw the input layer nodes
    \foreach \name / \y in {1,...,5}
    % This is the same as writing \foreach \name / \y in {1/1,2/2,3/3,4/4}
        \node[input neuron, pin=left:Input \#\y] (I-\name) at (0,-\y) {}; % {$p_\y$};

    % Draw the hidden layer nodes
    \foreach \name / \y in {1,...,5}
        \path[yshift=0.cm]
            node[hidden neuron] (H-\name) at (\layersep,-\y cm) {};

    % Draw the hidden layer nodes
    \foreach \name / \y in {1,...,5}
        \path[yshift=0.cm]
            node[hidden neuron] (H1-\name) at (\layersepp,-\y cm) {};


    % Draw the output layer node
    \node[output neuron,pin={[pin edge={->}]right:Output}, right of=H1-3] (O) {};

    % Connect every node in the input layer with every node in the
    % hidden layer.
    \foreach \source in {1,...,4}
        \foreach \dest in {1,...,5}
            \path (I-\source) edge (H-\dest);

    % Connect every node in the input layer with every node in the
    % hidden layer.
    \foreach \source in {1,...,5}
        \foreach \dest in {1,...,5}
            \path (H-\source) edge (H1-\dest);

    % Connect every node in the hidden layer with the output layer
    \foreach \source in {1,...,5}
        \path (H1-\source) edge (O);

    % Annotate the layers
    \node[annot,above of=H-1, node distance=1cm] (hl) {Hidden layer};
    \node[annot,above of=H1-1, node distance=1cm] (hl1) {Hidden layer};
    \node[annot,left of=hl] {Input layer};
    \node[annot,right of=hl1] {Output layer};
\end{tikzpicture}

\end{document}

绘制该图：

在此处输入图片描述

要删除前三个节点列中的倒数第二个（第 4 个）节点，我使用\ifthenelse以下代码：

\begin{tikzpicture}[shorten >=1pt,->,draw=black!50, node distance=\layersep,]
    \tikzstyle{every pin edge}=[<-,shorten <=1pt]
    \tikzstyle{neuron}=[circle,fill=black!25,minimum size=17pt,inner sep=0pt]
    \tikzstyle{input neuron}=[neuron, fill=green!50];
    \tikzstyle{output neuron}=[neuron, fill=red!50];
    \tikzstyle{hidden neuron}=[neuron, fill=blue!50];
    \tikzstyle{annot} = [text width=4em, text centered]

    % Draw the input layer nodes
    \foreach \name / \y in {1,...,5} 
    % This is the same as writing \foreach \name / \y in {1/1,2/2,3/3,4/4}
        \ifthenelse{\NOT 4 = \y }{
        \node[input neuron, pin=left:Input \#\y] (I-\name) at (0,-\y) {}; % {$p_\y$};
        }{$\vdots$}

    % Draw the hidden layer nodes
    \foreach \name / \y in {1,...,5}
      \ifthenelse{\NOT 4 = \y }{
        \path[yshift=0.cm]
            node[hidden neuron] (H-\name) at (\layersep,-\y cm) {};
      }{$\vdots$}

    % Draw the hidden layer nodes
    \foreach \name / \y in {1,...,5}
      \ifthenelse{\NOT 4 = \y }{
        \path[yshift=0.cm]
            node[hidden neuron] (H1-\name) at (\layersepp,-\y cm) {};
      }{$\vdots$}

    % Draw the output layer node
    \node[output neuron,pin={[pin edge={->}]right:Output}, right of=H1-3] (O) {};

    % Connect every node in the input layer with every node in the
    % hidden layer.
    \foreach \source in {1,...,5}
        \foreach \dest in {1,...,5}
        \ifthenelse{\NOT 4 = \y }{
            \path (I-\source) edge (H-\dest);
        }{}

    % Connect every node in the input layer with every node in the
    % hidden layer.
    \foreach \source in {1,...,5}
        \foreach \dest in {1,...,5}
        \ifthenelse{\NOT 4 = \y }{
            \path (H-\source) edge (H1-\dest);
        }{}

    % Connect every node in the hidden layer with the output layer
    \foreach \source in {1,...,5}
      \ifthenelse{\NOT 4 = \y }{
        \path (H1-\source) edge (O);
        }{}

    % Annotate the layers
    \node[annot,above of=H-1, node distance=1cm] (hl) {Hidden layer};
    \node[annot,above of=H1-1, node distance=1cm] (hl1) {Hidden layer};
    \node[annot,left of=hl] {Input layer};
    \node[annot,right of=hl1] {Output layer};
\end{tikzpicture}

但它不能编译，第一次出现以下错误ifthenelse

Latex Error: ./rnn_split_2.tex:103 Paragraph ended before \pgffor@next was complete.

答案1

主要问题是您不能将其放入\vdots环境中间tizpicture。相反，您需要将其放在节点内。这类似于\node at (0,0) {$\vdots$};。另一个问题是“长”\foreach语句需要用括号括起来。为了安全起见，我总是写

\foreach \name / \y in {1,...,5} {
...
}

您的一些测试涉及\y应该使用\dest或进行测试\source。除此之外，我一直使用 直线，\ifnum\y=4 ...\else ...\fi因为我更喜欢这样。进行这些更改后，您的代码将编译并生成：

在此处输入图片描述

以下是更新后的代码：

\documentclass[border=1mm]{standalone}
\usepackage{amsmath}
\usepackage{tikz,pgfplots}
%\usepackage{xifthen}
\pgfplotsset{compat=1.15}


\begin{document}
\pagestyle{empty}

\def\layersep{2.5cm}
\def\layersepp{5cm}

\begin{tikzpicture}[shorten >=1pt,->,draw=black!50, node distance=\layersep,]
    \tikzstyle{every pin edge}=[<-,shorten <=1pt]
    \tikzstyle{neuron}=[circle,fill=black!25,minimum size=17pt,inner sep=0pt]
    \tikzstyle{input neuron}=[neuron, fill=green!50];
    \tikzstyle{output neuron}=[neuron, fill=red!50];
    \tikzstyle{hidden neuron}=[neuron, fill=blue!50];
    \tikzstyle{annot} = [text width=4em, text centered]

    % Draw the input layer nodes
    \foreach \name / \y in {1,...,5} {
        \ifnum\y=4 \node at (0,-\y) {$\vdots$}; % {$p_\y$};
        \else
          \node[input neuron, pin=left:Input \#\y] (I-\name) at (0,-\y) {}; % {$p_\y$};
        \fi
    }

    % Draw the hidden layer nodes
    \foreach \name / \y in {1,...,5} {
        \ifnum\y=4 \node at  (\layersep,-\y cm) {$\vdots$}; % {$p_\y$};
        \else
          \path[yshift=0.cm] node[hidden neuron] (H-\name) at (\layersep,-\y cm) {};
        \fi
    }

    % Draw the hidden layer nodes
    \foreach \name / \y in {1,...,5} {
        \ifnum\y=4 \node at  (\layersepp,-\y cm) {$\vdots$}; % {$p_\y$};
        \else
          \path[yshift=0.cm] node[hidden neuron] (H1-\name) at (\layersepp,-\y cm) {};
        \fi
    }

    % Draw the output layer node
    \node[output neuron,pin={[pin edge={->}]right:Output}, right of=H1-3] (O) {};

    % Connect every node in the input layer with every node in the
    % hidden layer.
    \foreach \source in {1,...,5} {
        \ifnum\source=4\else
          \foreach \dest in {1,...,5} {
            \ifnum\dest=4\else
              \path (I-\source) edge (H-\dest);
            \fi
          }
        \fi
    }

    % Connect every node in the input layer with every node in the
    % hidden layer.
    \foreach \source in {1,...,5} {
      \ifnum\source=4\else
        \foreach \dest in {1,...,5} {
          \ifnum\dest=4\else
              \path (H-\source) edge (H1-\dest);
          \fi
        }
      \fi
    }

    % Connect every node in the hidden layer with the output layer
    \foreach \source in {1,...,5} {
      \ifnum\source=4\else
        \path (H1-\source) edge (O);
      \fi
    }

    % Annotate the layers
    \node[annot,above of=H-1, node distance=1cm] (hl) {Hidden layer};
    \node[annot,above of=H1-1, node distance=1cm] (hl1) {Hidden layer};
    \node[annot,left of=hl] {Input layer};
    \node[annot,right of=hl1] {Output layer};
\end{tikzpicture}

\end{document}

最后，\tiksstyle已经贬值了。这些天你应该使用\tikzset，但我没有改变这一点。

相关内容