合并分支 'caorunzhe' 到 'master'

Caorunzhe

查看合并请求 !955

Chapter15/Figures/figure-introducing-rnn-mechanism-into-transformer.tex

@@ -5,20 +5,20 @@
 
 \tikzstyle{tnode}=[rectangle,inner sep=0mm,minimum height=1.8em,minimum width=4em,rounded corners=5pt,thick,draw,fill=teal!20]
 \tikzstyle{stnode}=[rectangle,inner sep=0mm,minimum height=1.8em,minimum width=4em,rounded corners=5pt,thick,fill=red!20,draw]
-\tikzstyle{rnnnode}=[rectangle,inner sep=0mm,minimum height=2em,minimum width=6.5em,rounded corners=5pt,thick,fill=green!20,draw]
+\tikzstyle{rnnnode}=[rectangle,inner sep=0mm,minimum height=1.8em,minimum width=5em,rounded corners=5pt,thick,fill=green!20,draw]
 
-\tikzstyle{wnode}=[inner sep=0mm,minimum height=2em,minimum width=5em]
+\tikzstyle{wnode}=[inner sep=0mm,minimum height=2em,minimum width=4em]
 
 \begin{scope}[]
 
-\node [anchor=west,rnnnode] (r1) at (0, 0) {循环单元$\mathbi{h}_1$};
-\node [anchor=south,rnnnode] (r2) at ([xshift=0em,yshift=1em]r1.north){循环单元$\mathbi{h}_2$};
+\node [anchor=west,rnnnode] (r1) at (0, 0) {循环单元};
+\node [anchor=south,rnnnode] (r2) at ([xshift=0em,yshift=1em]r1.north){循环单元};
 \node [anchor=south] (r3) at ([xshift=0em,yshift=1em]r2.north){$\cdots$};
-\node [anchor=south,rnnnode] (r4) at ([xshift=0em,yshift=1em]r3.north){循环单元$\mathbi{h}_n$};
+\node [anchor=south,rnnnode] (r4) at ([xshift=0em,yshift=1em]r3.north){循环单元};
 
-\node [anchor=east,wnode,font=\footnotesize] (wr1) at ([xshift=-1em,yshift=0em]r1.west) {1时刻输入};
-\node [anchor=east,wnode,font=\footnotesize] (wr2) at ([xshift=-1em,yshift=0em]r2.west) {2时刻输入};
-\node [anchor=east,wnode,font=\footnotesize] (wr3) at ([xshift=-1em,yshift=0em]r4.west) {$n$时刻输入};
+\node [anchor=east,wnode,font=\footnotesize,align=left,minimum width=3em] (wr1) at ([xshift=-1em,yshift=0em]r1.west) {1时刻\\ 输入};
+\node [anchor=east,wnode,font=\footnotesize,align=left,minimum width=3em] (wr2) at ([xshift=-1em,yshift=0em]r2.west) {2时刻\\ 输入};
+\node [anchor=east,wnode,font=\footnotesize,align=left,minimum width=3em] (wr3) at ([xshift=-1em,yshift=0em]r4.west) {$n$时刻\\ 输入};
 
 \node [anchor=north,wnode] (input) at ([xshift=0em,yshift=-1em]r1.south) {$\mathbi{h}_0$};
 \node [anchor=south,wnode] (output) at ([xshift=0em,yshift=1em]r4.north) {输出};
@@ -34,11 +34,11 @@
 \draw[->,thick] ([xshift=0em,yshift=0em]wr2.east)--([xshift=0em,yshift=0em]r2.west);
 \draw[->,thick] ([xshift=0em,yshift=0em]wr3.east)--([xshift=0em,yshift=0em]r4.west);
 
-\node [anchor=north,font=\small] (label) at ([xshift=-4em,yshift=-0.5em]input.south) {(a)RNN};
+\node [anchor=north,font=\small] (label) at ([xshift=-3em,yshift=-0.7em]input.south) {(a)RNN};
 
 \end{scope}
 
-\begin{scope}[xshift=1.9in]
+\begin{scope}[xshift=1.85in]
 
 \node [anchor=west,stnode] (r1) at (0, 0) {第1层};
 \node [anchor=south,tnode] (r2) at ([xshift=0em,yshift=1em]r1.north){第2层};
@@ -60,20 +60,20 @@
 \draw[->,thick] ([xshift=0em,yshift=0em]r3.north)--([xshift=0em,yshift=0em]r4.south);
 \draw[->,thick] ([xshift=0em,yshift=0em]r4.north)--([xshift=0em,yshift=0em]output.south);
 
-\node [anchor=north,font=\small] (label) at ([xshift=-2em,yshift=-0.5em]input.south) {(b)原始Transformer模型};
+\node [anchor=north,font=\small] (label) at ([xshift=-1.5em,yshift=-0.7em]input.south) {(b)原始Transformer模型};
 
 \end{scope}
 
-\begin{scope}[xshift=3.7in]
+\begin{scope}[xshift=3.9in]
 
 \node [anchor=west,stnode] (r1) at (0, 0) {第1层};
 \node [anchor=south,stnode] (r2) at ([xshift=0em,yshift=1em]r1.north){第2层};
 \node [anchor=south] (r3) at ([xshift=0em,yshift=1em]r2.north){$\cdots$};
 \node [anchor=south,stnode] (r4) at ([xshift=0em,yshift=1em]r3.north){第$n$层};
 
-\node [anchor=east,wnode,font=\footnotesize,align=left,minimum width=4em] (wr1) at ([xshift=-1em,yshift=0em]r1.west) {1时刻编\\ 码向量};
-\node [anchor=east,wnode,font=\footnotesize,align=left,minimum width=4em] (wr2) at ([xshift=-1em,yshift=0em]r2.west) {2时刻编\\ 码向量};
-\node [anchor=east,wnode,font=\footnotesize,align=left,minimum width=4em] (wr3) at ([xshift=-1em,yshift=0em]r4.west) {$n$时刻编\\ 码向量};
+\node [anchor=east,wnode,font=\footnotesize,align=left] (wr1) at ([xshift=-1em,yshift=0em]r1.west) {1时刻\\ 编码向量};
+\node [anchor=east,wnode,font=\footnotesize,align=left] (wr2) at ([xshift=-1em,yshift=0em]r2.west) {2时刻\\ 编码向量};
+\node [anchor=east,wnode,font=\footnotesize,align=left] (wr3) at ([xshift=-1em,yshift=0em]r4.west) {$n$时刻\\ 编码向量};
 
 \node [anchor=north,wnode] (input) at ([xshift=0em,yshift=-1em]r1.south) {$\mathbi{h}_0$};
 \node [anchor=south,wnode] (output) at ([xshift=0em,yshift=1em]r4.north) {输出};
@@ -89,7 +89,7 @@
 \draw[->,thick] ([xshift=0em,yshift=0em]wr2.east)--([xshift=0em,yshift=0em]r2.west);
 \draw[->,thick] ([xshift=0em,yshift=0em]wr3.east)--([xshift=0em,yshift=0em]r4.west);
 
-\node [anchor=north,font=\small,align=left] (label) at ([xshift=-2em,yshift=0.2em]input.south) {(c)共享权重的\\ Transformer模型};
+\node [anchor=north,font=\small,align=left] (label) at ([xshift=-3em,yshift=-0.7em]input.south) {(c)共享权重的\\ Transformer模型};
 
 \end{scope}
 

Chapter15/Figures/figure-relative-position-coding-and-absolute-position-coding.tex

@@ -21,25 +21,28 @@
 \node [ffnnode,anchor=south] (ffn2) at ([yshift=0.5em]res3.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res4) at ([yshift=0.3em]ffn2.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 
-\node [anchor=north west,font=\scriptsize,align=center] (l1) at ([xshift=0.1em]ffn1.north east) {第 \\ 一 \\ 层};
-\node [anchor=north west,font=\scriptsize,align=center] (l2) at ([xshift=0.1em]ffn2.north east) {第 \\ $n$ \\ 层};
+\node [anchor=north west,font=\scriptsize,align=center,ublue] (l1) at ([xshift=0.1em]ffn1.north east) {第 \\ $1$ \\ 层};
+\node [anchor=north west,font=\scriptsize,align=center,ublue] (l2) at ([xshift=0.1em]ffn2.north east) {第 \\ $n$ \\ 层};
 \node [anchor=south east,font=\scriptsize] (l3) at ([yshift=3em]l1.north east) {};
-\node [anchor=north east,font=\scriptsize,align=center,opacity=0.0] (l4) at ([xshift=0.1em]ffn1.north west) {第 \\ 一 \\ 层};
+\node [anchor=north east,font=\scriptsize,align=center,opacity=0.0] (l4) at ([xshift=0.1em]ffn1.north west) {第 \\ $1$ \\ 层};
 \node [anchor=north east,font=\scriptsize,align=center,opacity=0.0] (l5) at ([xshift=0.1em]ffn2.north west) {第 \\ $n$ \\ 层};
 \node [anchor=south west,font=\scriptsize] (l6) at ([yshift=3em]l4.north west) {};
 
 \node [anchor=south west] (e1) at ([xshift=-1.4em,yshift=0.3em]res4.north west) {{编码器}};
 
+\node [anchor=north,minimum height=0.1em,minimum width=0.1em] (set1) at ([xshift=0em,yshift=0.3em]sa1.south) {};
+\node [anchor=north,minimum height=0.1em,minimum width=0.1em] (set2) at ([xshift=0em,yshift=0.3em]sa2.south) {};
+
 \begin{pgfonlayer}{background}
-	\node [rectangle,inner sep=0.6em,rounded corners=5pt,very thick,dotted,minimum height=1.4em,minimum width=3.5em,draw=red!40] [fit = (e1) (sa1) (l1) (l4)] (b4) {};
-	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=green!40,minimum height=1.4em,minimum width=7em] [fit = (l1) (sa1) (res2) (l4)] (b1) {};		
-	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=green!40,minimum height=1.4em,minimum width=7em] [fit = (dot1) (l3) (l6)] (b2) {};	
-	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=green!40,minimum height=1.4em,minimum width=7em] [fit = (l2) (sa2) (res4) (l5)] (b3) {};	
+	\node [rectangle,inner sep=0.6em,rounded corners=5pt,very thick,dotted,minimum height=1.4em,minimum width=3.5em,draw=red] [fit = (e1) (sa1) (l1) (l4) (set1)] (b4) {};
+	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=ublue,minimum height=1.4em,minimum width=7em] [fit = (l1) (sa1) (res2) (l4) (set1)] (b1) {};		
+	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=ublue,minimum height=1.4em,minimum width=7em] [fit = (dot1) (l3) (l6)] (b2) {};	
+	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=ublue,minimum height=1.4em,minimum width=7em] [fit = (l2) (sa2) (res4) (l5) (set2)] (b3) {};	
 \end{pgfonlayer}
 
-\node [inputnode,anchor=north west] (input1) at ([yshift=-1.1em,xshift=-0.5em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
-\node [] (add) at ([yshift=-1.7em,xshift=3.5em]sa1.south west) {$+$};
-\node [posnode,anchor=north east] (pos1) at ([yshift=-1.1em,xshift=1.6em]sa1.south east) {\tiny{$\textbf{Absolute Position}$}};
+\node [inputnode,anchor=north west] (input1) at ([yshift=-1.6em,xshift=-0.5em]sa1.south west) {\tiny{$\textbf{Embedding}$}};
+\node [] (add) at ([yshift=-2.2em,xshift=3.5em]sa1.south west) {$+$};
+\node [posnode,anchor=north east] (pos1) at ([yshift=-1.6em,xshift=1.6em]sa1.south east) {\tiny{$\textbf{Absolute Position}$}};
 
 \node [anchor=north] (wi) at ([yshift=-0.5em]pos1.south) {\scriptsize{词序信息}};
 
@@ -83,25 +86,28 @@
 \node [ffnnode,anchor=south] (ffn2) at ([yshift=0.5em]res3.north) {\tiny{$\textbf{Feed Forward Network}$}};
 \node [Resnode,anchor=south] (res4) at ([yshift=0.3em]ffn2.north) {\tiny{$\textbf{Add \& LayerNorm}$}};
 
-\node [anchor=north west,font=\scriptsize,align=center] (l1) at ([xshift=0.1em]ffn1.north east) {第 \\ 一 \\ 层};
-\node [anchor=north west,font=\scriptsize,align=center] (l2) at ([xshift=0.1em]ffn2.north east) {第 \\ $n$ \\ 层};
+\node [anchor=north west,font=\scriptsize,align=center,ublue] (l1) at ([xshift=0.1em]ffn1.north east) {第 \\ $1$ \\ 层};
+\node [anchor=north west,font=\scriptsize,align=center,ublue] (l2) at ([xshift=0.1em]ffn2.north east) {第 \\ $n$ \\ 层};
 \node [anchor=south east,font=\scriptsize] (l3) at ([yshift=3em]l1.north east) {};
-\node [anchor=north east,font=\scriptsize,align=center,opacity=0.0] (l4) at ([xshift=0.1em]ffn1.north west) {第 \\ 一 \\ 层};
+\node [anchor=north east,font=\scriptsize,align=center,opacity=0.0] (l4) at ([xshift=0.1em]ffn1.north west) {第 \\ $1$ \\ 层};
 \node [anchor=north east,font=\scriptsize,align=center,opacity=0.0] (l5) at ([xshift=0.1em]ffn2.north west) {第 \\ $n$ \\ 层};
 \node [anchor=south west,font=\scriptsize] (l6) at ([yshift=3em]l4.north west) {};
 
 \node [anchor=south west] (e1) at ([xshift=-1.4em,yshift=0.3em]res4.north west) {{编码器}};
 
+\node [anchor=north,minimum height=0.1em,minimum width=0.1em] (set1) at ([xshift=0em,yshift=0.3em]sa1.south) {};
+\node [anchor=north,minimum height=0.1em,minimum width=0.1em] (set2) at ([xshift=0em,yshift=0.3em]sa2.south) {};
+
 \begin{pgfonlayer}{background}
-	\node [rectangle,inner sep=0.6em,rounded corners=5pt,very thick,dotted,minimum height=1.4em,minimum width=3.5em,draw=red!40] [fit = (e1) (sa1) (l1) (l4)] (b4) {};
-	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=green!40,minimum height=1.4em,minimum width=7em] [fit = (l1) (sa1) (res2) (l4)] (b1) {};		
-	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=green!40,minimum height=1.4em,minimum width=7em] [fit = (dot1) (l3) (l6)] (b2) {};	
-	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=green!40,minimum height=1.4em,minimum width=7em] [fit = (l2) (sa2) (res4) (l5)] (b3) {};	
+	\node [rectangle,inner sep=0.6em,rounded corners=5pt,very thick,dotted,minimum height=1.4em,minimum width=3.5em,draw=red] [fit = (e1) (sa1) (l1) (l4) (set1)] (b4) {};
+	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=ublue,minimum height=1.4em,minimum width=7em] [fit = (l1) (sa1) (res2) (l4) (set1)] (b1) {};		
+	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=ublue,minimum height=1.4em,minimum width=7em] [fit = (dot1) (l3) (l6)] (b2) {};	
+	\node [rectangle,inner sep=0.3em,rounded corners=5pt,very thick,dotted,draw=ublue,minimum height=1.4em,minimum width=7em] [fit = (l2) (sa2) (res4) (l5) (set2)] (b3) {};	
 \end{pgfonlayer}
 
-\node [inputnode,anchor=north west] (input1) at ([yshift=-1.1em,xshift=-0.5em]sa1.south west) {\tiny{Embedding}};
-\node [] (add) at ([yshift=-1.7em,xshift=3.5em]sa1.south west) {$+$};
-\node [posnode,anchor=north east] (pos1) at ([yshift=-1.1em,xshift=1.5em]sa1.south east) {\tiny{Absolute Position}};
+\node [inputnode,anchor=north west] (input1) at ([yshift=-1.6em,xshift=-0.5em]sa1.south west) {\tiny{Embedding}};
+\node [] (add) at ([yshift=-2.2em,xshift=3.5em]sa1.south west) {$+$};
+\node [posnode,anchor=north east] (pos1) at ([yshift=-1.6em,xshift=1.5em]sa1.south east) {\tiny{Absolute Position}};
 
 \node [anchor=north] (wi) at ([yshift=-0.5em]pos1.south) {\scriptsize{词序信息}};
 
@@ -130,9 +136,9 @@
 \draw[->,standard] ([xshift=0em]wi.east) -- ([xshift=3.2em,yshift=0em]wi.east) -- ([xshift=-0em,yshift=0em]pos2.south);
 \draw[->,standard] ([xshift=0em]wi.east) -- ([xshift=6.7em,yshift=0em]wi.east) -- ([xshift=-0em,yshift=0em]pos3.south);
 \draw[->,standard] ([xshift=0em]wi.east) -- ([xshift=10.2em,yshift=0em]wi.east) -- ([xshift=-0em,yshift=0em]pos4.south);
-\draw[->,standard] ([xshift=0em]pos2.north) -- ([xshift=0em,yshift=1.6em]pos2.north) -- ([xshift=-0em,yshift=0em]sa1.east);
-\draw[->,standard] ([xshift=0em]pos3.north) -- ([xshift=0em,yshift=9em]pos3.north) -- ([xshift=-0em,yshift=0em]dot1.east);
-\draw[->,standard] ([xshift=0em]pos4.north) -- ([xshift=0em,yshift=11.7em]pos4.north) -- ([xshift=-0em,yshift=0em]sa2.east);
+\draw[->,standard] ([xshift=0em]pos2.north) -- ([xshift=0em,yshift=2.1em]pos2.north) -- ([xshift=-0em,yshift=0em]sa1.east);
+\draw[->,standard] ([xshift=0em]pos3.north) -- ([xshift=0em,yshift=9.6em]pos3.north) -- ([xshift=-0em,yshift=0em]dot1.east);
+\draw[->,standard] ([xshift=0em]pos4.north) -- ([xshift=0em,yshift=12.3em]pos4.north) -- ([xshift=-0em,yshift=0em]sa2.east);
 
 
 \begin{pgfonlayer}{background}

Chapter15/Figures/figure-relative-position-weight.tex

@@ -27,6 +27,9 @@
     {0/0/8, 1/0/9, 2/0/10, 3/0/11, 4/0/12, 5/0/13, 6/0/14}
     \node[anchor=north] (n\k) at ([xshift=-0em,yshift=-0.5em]a\i\j.south) {\i};
 
+\node [anchor=east] (l1) at ([xshift=-0.3em,yshift=0em]n8.west) {$i$};
+\node [anchor=north] (l2) at ([xshift=0em,yshift=-0em]n7.south) {$j$};
+
 %\node [anchor=north] (n1) at ([xshift=0em,yshift=0em]a00.south west) {};
 
 \end{scope}