1. 快速入門使用tikz繪制深度學(xué)習(xí)網(wǎng)絡(luò)圖

        共 13063字,需瀏覽 27分鐘

         ·

        2020-09-16 14:03



        【GiantPandaCV導(dǎo)語】本文主要介紹最最最基礎(chǔ)的tikz命令和一些繪制CNN時需要的基礎(chǔ)的LaTeX知識,希望能在盡可能短的時間內(nèi)學(xué)會并實(shí)現(xiàn)使用tikz這個LaTeX工具包來繪制卷積神經(jīng)網(wǎng)絡(luò)示意圖。

        https://github.com/HarisIqbal88/PlotNeuralNet

        之前看到tikz可以畫出這種圖,感覺特別專業(yè),所以萌發(fā)出了解一下tikz的想法。

        1. overleaf平臺

        在電腦上安裝過LaTeX都知道,LaTeX安裝包巨大,并且安裝速度緩慢,下載和安裝的時間需要幾乎一下午才能完成。慶幸的是有一個平臺可以在線編譯文檔,那就是overleaf,如今overleaf也推出了中文版本網(wǎng)站:https://cn.overleaf.com/ 以下代碼全部是在overleaf平臺上編寫運(yùn)行得到的。

        主頁面
        進(jìn)入其中一個項目

        最左側(cè)是項目文件列表,中間是代碼編輯區(qū),右側(cè)是可視化區(qū),十分方便,只要網(wǎng)絡(luò)通常,就可以方便地得到結(jié)果。并且這個平臺提供了好多模板,可以直接使用,太太太太太棒啦。

        2. 快速入門tikz

        快速熟悉還是要推薦《minimaltikz》這本電子書,可以直接訪問http://cremeronline.com/LaTeX/minimaltikz.pdf獲取或者在后臺回復(fù)latex獲取。

        電子書封面

        這本書一共24頁,算是盡量壓縮了內(nèi)容了,在這一節(jié)中將分析一下其中給的幾個例子,用于快速入門:

        所有tikz繪制圖像的代碼都應(yīng)該在tikzpicture這個環(huán)境中使用。

        \begin{tikzpicture}
        ...
        \end{tikzpicture}

        直角坐標(biāo)系下:($$)的形式代表二維坐標(biāo)系中的一個點(diǎn),單位是cm。

        極坐標(biāo)系下:(:$\theta$代表極角,單位是度。

        \coordinate可以對某個點(diǎn)進(jìn)行重命名如:

        \coordinate (s) at (0,1);

        2.1 直線

        那最基礎(chǔ)的畫幾條線的實(shí)現(xiàn)是通過\draw完成:

            \begin{tikzpicture}
        \draw[help lines] (0,0) grid(3,3);
        \coordinate (a) at (0,1);
        \coordinate (b) at (3,3);
        \coordinate (c) at (2,0);
        \draw (a) -- (b) -- (c) --cycle;
        \end{tikzpicture}

        --符號代表兩點(diǎn)之間的連線,可以連續(xù)鏈接多段。cycle代表讓路徑回到起點(diǎn),生成閉合路徑。

        結(jié)果展示

        \draw還可以添加選項,比如讓線變粗、變紅、箭頭等需求,都很簡單。

        \begin{tikzpicture}[scale=1]
        \draw[help lines] (0,0) grid(5,5);
        \draw (0,0) -- (1,2)--(3,0) --(5,5);
        \draw [->] (0,0) -- (2,1);
        \draw [<-] (2,3) -- (5,0);
        \draw [|->] (0.5,3) -- (0,4);
        \draw [<->] (0,6) -- (0,0) -- (6,0);
        \end{tikzpicture}
        不同的箭頭
        \begin{tikzpicture}
        \draw[help lines] (0,0) grid(5,5);
        \draw[thick] (0.5, 0.5) -- (3,3);
        % [ultra thick, thick, thin, very thick]
        \draw[line width=0.2cm] (1,0) -- (3,2);
        \end{tikzpicture}
        粗細(xì)控制
        \begin{tikzpicture}
        \draw[help lines] (0,0) grid(5,5);
        \draw[ultra thick, dotted] (0,0) -- (2,3);
        \draw[line width=0.2cm, dotted,red] (2,2) -- (4,0);
        %[red, blue, green, cyan, magenta, yellow, black, gray, darkgray, lightgray, browbn, lime, olive, orange, pink, purple, teal, violet, white]
        \end{tikzpicture}
        顏色控制

        2.2 曲線

        畫一些曲線就需要使用circle、rectangle、arc等進(jìn)行約束。

        \begin{tikzpicture}
        \draw[help lines] (0,0) grid(5,5);
        \draw[blue] (1,1) rectangle(3,3); % 正方形 需要左下角坐標(biāo)和右上角坐標(biāo)
        \draw[red] (2,2) circle[radius=2]; %圓形 需要圓心坐標(biāo)和半徑
        \draw[green] (1,0) arc [radius=1,start angle=180,end angle=360];
        \draw[<->, rounded corners, thick, purple] (0,5) -- (0,0) -- (5,0);
        \end{tikzpicture}
        結(jié)果展示
        \begin{tikzpicture}
        \draw[help?lines]?(0,0)?grid(6,3);
        \draw[blue,?thick]?(0,0)?to[out=90,in=180]?(1,1)?to[in=270,out=360]?(2,2)
        to[in=180,out=90]?(3,3)?to[in=90,out=360]?(4,2)?to[in=180,out=270]?(5,1)?
        to[in=90,?out=0]?(6,0);
        \end{tikzpicture}

        這是練習(xí)畫弧線的時候想練習(xí)的一個例子,結(jié)果如下

        結(jié)果展示

        in代表進(jìn)入的角度,out代表出來時候的角度,為了方便,筆者畫了一個輔助圖,對照代碼方便理解。

        參考

        2.3 畫函數(shù)曲線

        \begin{tikzpicture}[xscale=6,yscale=6]
        \draw[<->] (0,0.8) -- (0,0) -- (0.8,0);
        \draw[green,thick,domain=0:0.5]
        plot(\x, {0.025+\x*\x});
        \draw[red, thick, domain=0:0.5]
        plot(\x, {sqrt(\x)});
        \draw[blue, thick, domain=0:0.5]
        plot(\x, {abs(\x)});
        \end{tikzpicture}

        domain限制變量范圍,然后可以畫圖,結(jié)果如下:

        繪制函數(shù)曲線

        2.4 填充

        \begin{tikzpicture}
        \draw[fill=red,ultra thick] (0,0) rectangle(1,1);
        \draw[fill=red,ultra thin, red] (2,0) rectangle(3,1);
        \draw[fill] (5,0) circle[radius=1];
        \draw [fill=orange] (9,0) rectangle (11,1);
        \draw [fill=white] (9.25,0.25) rectangle (10,1.5);
        \path [fill=gray] (0,-2) rectangle (1.5,-3);
        \draw [fill=yellow] (2,-2) rectangle (3.5,-3);
        \end{tikzpicture}

        通過fill參數(shù)控制結(jié)果,效果如下:

        填充結(jié)果

        2.6 添加文字

        使用\node

        \node?[]?()?at?()?{};

        舉個例子:

        \begin{tikzpicture}[scale=2]
        \draw [thick, <->] (0,1) -- (0,0) -- (1,0);
        \draw[fill] (1,1) circle [radius=0.025];
        \node [below right, red] at (.5,.75) {below right};
        \node [above left, green] at (.5,.75) {above left};
        \node [below left, purple] at (.5,.75) {below left};
        \node [above right, magenta] at (.5,.75) {above right};
        \end{tikzpicture}
        添加文字效果

        其實(shí)CNN畫圖主要用的是畫一條線的功能,下面來看如何畫CNN。

        3. 繪制一個CNN模塊

        對于一個初學(xué)者來說,https://github.com/HarisIqbal88/PlotNeuralNet 這個庫雖然畫的很好,但是難度曲線太高了,退而求其次,使用https://github.com/pprp/SimpleCVReproduction/tree/master/tikz_cnn 進(jìn)行解析。

        首先介紹一個LaTeX中用于封裝的命令,\newcommand,當(dāng)我們不希望寫很長的命令,那就需要類似函數(shù)的一個方式,封裝好固定的操作,根據(jù)傳入?yún)?shù)完成執(zhí)行。

        \newcommand<命令>[<參數(shù)個數(shù)>][<首參數(shù)默認(rèn)值>]{<具體的定義>}

        舉一個例子:

        \newcommand\loves[2]{#1 喜歡 #2}
        \loves{我}{你}

        輸出結(jié)果就是:我喜歡你

        \newcommand{\networkLayer}[9]{
        % Define the macro.
        % 1st argument: Height and width of the layer rectangle slice.
        % 2nd argument: Depth of the layer slice
        % 3rd argument: X Offset --> use it to offset layers from previously drawn layers.
        % 4th argument: Y Offset --> Use it when an output needs to be fed to multiple layers that are on the same X offset.
        % 5th argument: Z Offset --> Use to offset layers from previous
        % 6th argument: Options for filldraw.
        % 7th argument: Text to be placed below this layer.
        % 8th argument: Name of coordinates. When name = "start" this resets the offset counter
        % 9th argument: list of nodes to connect to (previous layers)
        % 全局變量
        \xdef\totalOffset{\totalOffset}
        \ifthenelse{\equal{#8} {start}}
        {\FPset{totalOffset}{0}}
        {}
        \FPeval\currentOffset{0+(totalOffset)+(#3)}

        \def\hw{#1} % Used to distinguish input resolution for current layer.
        \def\b{0.02}
        \def\c{#2} % Width of the cube to distinguish number of input channels for current layer.
        \def\x{\currentOffset} % X offset for current layer.
        \def\y{#4} % Y offset for current layer.
        \def\z{#5} % Z offset for current layer.
        \def\inText{#7}

        % Define references to points on the cube surfaces
        \coordinate (#8_front) at (\x+\c , \z , \y);
        \coordinate (#8_back) at (\x , \z , \y);
        \coordinate (#8_top) at (\x+\c/2, \z+\hw/2, \y);
        \coordinate (#8_bottom) at (\x+\c/2, \z-\hw/2, \y);

        % Define cube coords
        \coordinate (blr) at (\c+\x, -\hw/2+\z, -\hw/2+\y); %back lower right
        \coordinate (bur) at (\c+\x, \hw/2+\z, -\hw/2+\y); %back upper right
        \coordinate (bul) at (0 +\x, \hw/2+\z, -\hw/2+\y); %back upper left
        \coordinate (fll) at (0 +\x, -\hw/2+\z, \hw/2+\y); %front lower left
        \coordinate (flr) at (\c+\x, -\hw/2+\z, \hw/2+\y); %front lower right
        \coordinate (fur) at (\c+\x, \hw/2+\z, \hw/2+\y); %front upper right
        \coordinate (ful) at (0 +\x, \hw/2+\z, \hw/2+\y); %front upper left


        % Draw connections from other points to the back of this node
        \ifthenelse{\equal{#9} {}}
        {} % 為空什么都不做
        { % 非空 開始畫層與層之間的連線
        \foreach \val in #9
        % \val = start_front
        \draw[line width=0.3mm] (\val)--(#8_back);
        }

        % Draw the layer body.
        % back plane
        \draw[line width=0.3mm](blr) -- (bur) -- (bul);
        % front plane
        \draw[line width=0.3mm](fll) -- (flr) node[midway,below] {\inText} -- (fur) -- (ful) -- (fll);
        \draw[line width=0.3mm](blr) -- (flr);
        \draw[line width=0.3mm](bur) -- (fur);
        \draw[line width=0.3mm](bul) -- (ful);

        % Recolor visible surfaces
        % front plane
        \filldraw[#6] ($(fll)+(\b,\b,0)$) -- ($(flr)+(-\b,\b,0)$) -- ($(fur)+(-\b,-\b,0)$) -- ($(ful)+(\b,-\b,0)$) -- ($(fll)+(\b,\b,0)$);
        \filldraw[#6] ($(ful)+(\b,0,-\b)$) -- ($(fur)+(-\b,0,-\b)$) -- ($(bur)+(-\b,0,\b)$) -- ($(bul)+(\b,0,\b)$);

        % Colored slice.
        \ifthenelse {\equal{#6} {}}
        {} % Do not draw colored slice if #6 is blank.
        % Else, draw a colored slice.
        {\filldraw[#6] ($(flr)+(0,\b,-\b)$) -- ($(blr)+(0,\b,\b)$) -- ($(bur)+(0,-\b,\b)$) -- ($(fur)+(0,-\b,-\b)$);}

        \FPeval\totalOffset{0+(currentOffset)+\c}

        \draw[ultra thick, red] (#8_back) circle[radius=0.02];
        \node[left] at (#8_back) {back};

        \draw[ultra thick, red] (#8_top) circle[radius=0.02];
        \node[above] at (#8_top) {top};

        \draw[ultra thick, red] (#8_bottom) circle[radius=0.02];
        \node[below] at (#8_bottom) {bottom};

        \draw[ultra thick, red] (#8_front) circle[radius=0.02];
        \node[left] at (#8_front) {front};
        }

        假設(shè)以下命令調(diào)用,結(jié)果會是什么?

        \begin{tikzpicture}[scale=2]
        \draw[help lines] (0,0) grid(2,2);
        \draw[->,thick] (0,0,0) -- (0,0,2);
        \draw[->,thick] (0,0,0) -- (0,2,0);
        \draw[->,thick] (0,0,0) -- (2,0,0);
        \draw[->,thick] (0,0,0) -- (2,2,0);
        \draw[->,thick] (0,0,0) -- (1,2,0);
        \draw[->,thick] (0,0,0) -- (0,2,2);
        \draw[->,thick] (0,0,0) -- (2,0,2);
        \draw[dotted,thick] (0,0,2) -- (0,2,2);
        \draw[dotted,thick] (0,2,0) -- (0,2,2);
        \draw[dotted,thick] (0,0,2) -- (2,0,2);
        \draw[dotted,thick] (2,0,0) -- (2,0,2);
        \draw[dotted,thick] (1,0,0) -- (1,0,2);
        \draw[dotted,thick] (0,0,1) -- (2,0,1);
        \draw[<->, thick] (0,2) -- (0,0) -- (2,0);
        %HW -D - x- y- z - fill color - text - 坐標(biāo) - 鏈接
        \networkLayer{1}{0.5}{0}{0}{0}{color=green!20}{conv1}{}{}
        \end{tikzpicture}

        顯示結(jié)果如下:

        可視化一個模塊

        卷積神經(jīng)網(wǎng)絡(luò)的示意圖實(shí)際上是一個個立方體構(gòu)成的,立方體之間可能會有額外連線,代表特征融合;還可能需要題注,為這個特征圖立方體進(jìn)行命名;必須要有立方體的位置信息,長寬高;還需要顏色填充的功能;

        綜合以上需求,這個函數(shù)提供了9個參數(shù)分別是:

        • #1 H&W 控制立方體右側(cè)這一面的高度,默認(rèn)為正方形。
        • #2 Depth 控制深度
        • #3 X 方向上的偏置
        • #4 Y方向上的偏置
        • #5 Z方向上的偏置
        • #6 填充的顏色
        • #7 Text展示的文本,放在最下側(cè)
        • #8 坐標(biāo)名稱,通過命名便于#9訪問
        • #9 通過名稱指定連接位置,用于連接前方層的時候使用
        前兩個參數(shù)示意圖

        由于每繪制一個立方體,右側(cè)立方體的X偏置就應(yīng)該加上左側(cè)立方體的Depth值,這部分代碼這樣處理的。

        \FPset{totalOffset}{0} % 設(shè)置全局變量totaloffset	
        \xdef\totalOffset{\totalOffset}
        \ifthenelse{\equal{#8} {start}}
        % 如果#8坐標(biāo)名稱為start,那么將totaloffset歸零
        {\FPset{totalOffset}{0}}
        {}% 否則什么都不做
        \FPeval\currentOffset{0+(totalOffset)+(#3)}
        % 計算當(dāng)前offset也就是#3 X+totalOffset

        賦值過程:

        \def\hw{#1} % Used to distinguish input resolution for current layer.
        \def\b{0.02}
        \def\c{#2} % Width of the cube to distinguish number of input channels for current layer.
        \def\x{\currentOffset} % X offset for current layer.
        \def\y{#4} % Y offset for current layer.
        \def\z{#5} % Z offset for current layer.
        \def\inText{#7}

        計算立方體表面坐標(biāo)(將點(diǎn)可視化是額外添加的,為了便于理解)

        % Define references to points on the cube surfaces
        \coordinate (#8_front) at (\x+\c , \z , \y);
        \coordinate (#8_back) at (\x , \z , \y);
        \coordinate (#8_top) at (\x+\c/2, \z+\hw/2, \y);
        \coordinate (#8_bottom) at (\x+\c/2, \z-\hw/2, \y);

        計算7個頂點(diǎn)位置,被擋住的也可以計算,但是因?yàn)檫@里不打算繪制所以不計算。

        7個頂點(diǎn)示意圖
        %?Define?cube?coords
        \coordinate?(blr)?at?(\c+\x,??-\hw/2+\z,??-\hw/2+\y);?%back?lower?right
        \coordinate?(bur)?at?(\c+\x,???\hw/2+\z,??-\hw/2+\y);?%back?upper?right
        \coordinate?(bul)?at?(0?+\x,???\hw/2+\z,??-\hw/2+\y);?%back?upper?left
        \coordinate?(fll)?at?(0?+\x,??-\hw/2+\z,???\hw/2+\y);?%front?lower?left
        \coordinate?(flr)?at?(\c+\x,??-\hw/2+\z,???\hw/2+\y);?%front?lower?right
        \coordinate?(fur)?at?(\c+\x,???\hw/2+\z,???\hw/2+\y);?%front?upper?right
        \coordinate?(ful)?at?(0?+\x,???\hw/2+\z,???\hw/2+\y);?%front?upper?left

        繪制立方塊之間的連線:

        % Draw connections from other points to the back of this node
        \ifthenelse{\equal{#9} {}}
        {} % 為空什么都不做
        { % 非空 開始畫層與層之間的連線
        \foreach \val in #9
        % \val = start_front
        \draw[line width=0.3mm] (\val)--(#8_back);
        }

        繪制立方體主體部分,也就是將7個點(diǎn)連接起來。

        % back plane
        \draw[line width=0.3mm](blr) -- (bur) -- (bul);
        % front plane
        \draw[line width=0.3mm](fll) -- (flr) node[midway,below] {\inText} -- (fur) -- (ful) -- (fll);
        \draw[line width=0.3mm](blr) -- (flr);
        \draw[line width=0.3mm](bur) -- (fur);
        \draw[line width=0.3mm](bul) -- (ful);

        填充顏色:

        % front plane
        \filldraw[#6] ($(fll)+(\b,\b,0)$) -- ($(flr)+(-\b,\b,0)$) -- ($(fur)+(-\b,-\b,0)$) -- ($(ful)+(\b,-\b,0)$) -- ($(fll)+(\b,\b,0)$);
        \filldraw[#6] ($(ful)+(\b,0,-\b)$) -- ($(fur)+(-\b,0,-\b)$) -- ($(bur)+(-\b,0,\b)$) -- ($(bul)+(\b,0,\b)$);

        % Colored slice.
        \ifthenelse {\equal{#6} {}}
        {} % Do not draw colored slice if #6 is blank.
        % Else, draw a colored slice.
        {\filldraw[#6] ($(flr)+(0,\b,-\b)$) -- ($(blr)+(0,\b,\b)$) -- ($(bur)+(0,-\b,\b)$) -- ($(fur)+(0,-\b,-\b)$);}
        一個卷積神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)圖

        上邊的圖是通過以下代碼生成的:

        \begin{tikzpicture}

        % INPUT
        \networkLayer{3.0}{0.03}{0.0}{0.0}{0.0}{color=gray!80}{}{start}{}

        % ENCODER
        \networkLayer{3.0}{0.1}{0.5}{0.0}{0.0}{color=white}{conv}{}{} % S1
        \networkLayer{3.0}{0.1}{0.1}{0.0}{0.0}{color=white}{}{}{} % S2
        \networkLayer{2.5}{0.2}{0.1}{0.0}{0.0}{color=white}{conv}{}{} % S1
        \networkLayer{2.5}{0.2}{0.1}{0.0}{0.0}{color=white}{}{}{} % S2
        \networkLayer{2.0}{0.4}{0.1}{0.0}{0.0}{color=white}{conv}{}{} % S1
        \networkLayer{2.0}{0.4}{0.1}{0.0}{0.0}{color=white}{}{}{} % S2
        \networkLayer{1.5}{0.8}{0.1}{0.0}{0.0}{color=white}{conv}{}{} % S1
        \networkLayer{1.5}{0.8}{0.1}{0.0}{0.0}{color=white}{}{}{} % S2
        \networkLayer{1.0}{1.5}{0.1}{0.0}{0.0}{color=white}{conv}{}{} % S1
        \networkLayer{1.0}{1.5}{0.1}{0.0}{0.0}{color=white}{}{mid}{} % S2

        \networkLayer{1.0}{0.5}{1.5}{0.0}{-1.5}{color=green!50}{}{bot}{{mid_front}}
        \networkLayer{1.0}{0.5}{-0.5}{0.0}{1.5}{color=green!50}{}{top}{{mid_front}}
        \networkLayer{1.0}{0.5}{1.5}{0.0}{0.0}{color=blue!50}{sum}{}{{bot_front,top_front}}

        % DECODER
        \networkLayer{1.0}{1.5}{0.1}{0.0}{0.0}{color=white}{deconv}{}{} % S1
        \networkLayer{1.0}{1.5}{0.1}{0.0}{0.0}{color=white}{}{}{} % S2
        \networkLayer{1.5}{0.8}{0.1}{0.0}{0.0}{color=white}{deconv}{}{} % S1
        \networkLayer{1.5}{0.8}{0.1}{0.0}{0.0}{color=white}{}{}{} % S2
        \networkLayer{2.0}{0.4}{0.1}{0.0}{0.0}{color=white}{}{}{} % S1
        \networkLayer{2.0}{0.4}{0.1}{0.0}{0.0}{color=white}{}{}{} % S2
        \networkLayer{2.5}{0.2}{0.1}{0.0}{0.0}{color=white}{}{}{} % S1
        \networkLayer{2.5}{0.2}{0.1}{0.0}{0.0}{color=white}{}{}{} % S2
        \networkLayer{3.0}{0.1}{0.1}{0.0}{0.0}{color=white}{}{}{} % S1
        \networkLayer{3.0}{0.1}{0.1}{0.0}{0.0}{color=white}{}{}{} % S2

        % OUTPUT
        \networkLayer{3.0}{0.05}{0.9}{0.0}{0.0}{color=red!40}{}{}{} % Pixelwise segmentation with classes.

        \end{tikzpicture}

        需要注意的是#8和#9命令,mid_front代表的是鏈接#8=mid的front部分,front也可以被top、back、bottom取代。

        4. 資源推薦

        https://cn.overleaf.com/project/5e8c38c31cccb20001a4998d

        https://cn.overleaf.com/project/5f50b21ae802b6000155ec4f

        https://github.com/HarisIqbal88/PlotNeuralNet

        https://github.com/pprp/SimpleCVReproduction/tree/master/tikz_cnn

        - END -


        對文章有疑問或者希望加群交流,可以添加筆者微信


        瀏覽 106
        點(diǎn)贊
        評論
        收藏
        分享

        手機(jī)掃一掃分享

        分享
        舉報
        評論
        圖片
        表情
        推薦
        點(diǎn)贊
        評論
        收藏
        分享

        手機(jī)掃一掃分享

        分享
        舉報
          
          

            1. 男女视频在线观看网站 | 永久中文字幕 | 扒开双腿猛进入校花 | 亚洲精品分类逼逼 | 激情五月天综合 |