合并分支 'mengxia' 到 'caorunzhe'

14编辑修改

查看合并请求 !1058

Chapter14/Figures/figure-comparison-of-different-attention-method.tex

@@ -23,11 +23,11 @@
 \node[attnnode,anchor=south] (attn11) at ([yshift=0.1\hnode]layer11.south) {};
 \node[anchor=north west,inner sep=4pt,font=\small] () at (attn11.north west) {注意力};
 \node[anchor=south,inner sep=0pt] (out11) at ([yshift=0.3\hseg]attn11.north) {$\cdots$};
-\node[thinnode,anchor=south west,thick,draw=dblue,text=black] (q11) at ([xshift=0.1\wseg,yshift=0.2\hseg]attn11.south west) {$Q^n$};
-\node[thinnode,anchor=south,thick,draw=orange,text=black] (k11) at ([yshift=0.2\hseg]attn11.south) {$K^n$};
-\node[thinnode,anchor=south east,thick,draw=purple,text=black] (v11) at ([xshift=-0.1\wseg,yshift=0.2\hseg]attn11.south east) {$V^n$};
-\node[fatnode,anchor=south,thick,draw] (s11) at ([xshift=0.5\wseg,yshift=0.8\hseg]q11.north east) {$S^n\!=\!S(Q^n\!\cdot\!K^n)$};
-\node[fatnode,anchor=south,thick,draw] (a11) at ([xshift=0.45\wseg,yshift=1.3\hseg+0.6\hnode]k11.north east) {$A^n\!=\!S^n\!\cdot\!V$};
+\node[thinnode,anchor=south west,thick,draw=dblue,text=black] (q11) at ([xshift=0.1\wseg,yshift=0.2\hseg]attn11.south west) {${\mathbi Q}^n$};
+\node[thinnode,anchor=south,thick,draw=orange,text=black] (k11) at ([yshift=0.2\hseg]attn11.south) {${\mathbi K}^n$};
+\node[thinnode,anchor=south east,thick,draw=purple,text=black] (v11) at ([xshift=-0.1\wseg,yshift=0.2\hseg]attn11.south east) {${\mathbi V}^n$};
+\node[fatnode,anchor=south,thick,draw] (s11) at ([xshift=0.5\wseg,yshift=0.8\hseg]q11.north east) {${\mathbi S}^n\!=\!{\mathbi S}({\mathbi Q}^n\!\cdot\!{\mathbi K}^n)$};
+\node[fatnode,anchor=south,thick,draw] (a11) at ([xshift=0.45\wseg,yshift=1.3\hseg+0.6\hnode]k11.north east) {${\mathbi A}^n\!=\!{\mathbi S}^n\!\cdot\!{\mathbi V}$};
 \begin{scope}[fill=black!100]
     \draw[-latex',thick,draw=black!100] (q11.north) .. controls +(north:0.5\hseg) and +(south:0.8\hseg) .. (s11.south);
     \draw[-latex',thick,draw=black!100] (k11.north) .. controls +(north:0.5\hseg) and +(south:0.8\hseg) .. (s11.south);
@@ -43,11 +43,11 @@
 \node[attnnode,anchor=south] (attn12) at ([yshift=0.1\hnode]layer12.south) {};
 \node[anchor=north west,inner sep=4pt,font=\small] () at (attn12.north west) {注意力};
 \node[anchor=south,inner sep=0pt] (out12) at ([yshift=0.3\hseg]attn12.north) {$\cdots$};
-\node[thinnode,anchor=south west,thick,draw=dblue!40,text=black!40] (q12) at ([xshift=0.1\wseg,yshift=0.2\hseg]attn12.south west) {$Q^n$};
-\node[thinnode,anchor=south,thick,draw=orange!40,text=black!40] (k12) at ([yshift=0.2\hseg]attn12.south) {$K^n$};
-\node[thinnode,anchor=south east,thick,draw=purple,text=black] (v12) at ([xshift=-0.1\wseg,yshift=0.2\hseg]attn12.south east) {$V^n$};
-\node[fatnode,anchor=south,thick,densely dashed,draw] (s12) at ([xshift=0.5\wseg,yshift=0.8\hseg]q12.north east) {$S^n\!=\!S^m$};
-\node[fatnode,anchor=south,thick,draw] (a12) at ([xshift=0.45\wseg,yshift=1.3\hseg+0.6\hnode]k12.north east) {$A^n\!=\!S^n\!\cdot\!V$};
+\node[thinnode,anchor=south west,thick,draw=dblue!40,text=black!40] (q12) at ([xshift=0.1\wseg,yshift=0.2\hseg]attn12.south west) {${\mathbi Q}^n$};
+\node[thinnode,anchor=south,thick,draw=orange!40,text=black!40] (k12) at ([yshift=0.2\hseg]attn12.south) {${\mathbi K}^n$};
+\node[thinnode,anchor=south east,thick,draw=purple,text=black] (v12) at ([xshift=-0.1\wseg,yshift=0.2\hseg]attn12.south east) {${\mathbi V}^n$};
+\node[fatnode,anchor=south,thick,densely dashed,draw] (s12) at ([xshift=0.5\wseg,yshift=0.8\hseg]q12.north east) {${\mathbi S}^n\!=\!{\mathbi S}^m$};
+\node[fatnode,anchor=south,thick,draw] (a12) at ([xshift=0.45\wseg,yshift=1.3\hseg+0.6\hnode]k12.north east) {${\mathbi A}^n\!=\!{\mathbi S}^n\!\cdot\!{\mathbi V}$};
 \begin{scope}[fill=black!40]
     \draw[-latex',thick,draw=black!40] (q12.north) .. controls +(north:0.5\hseg) and +(south:0.8\hseg) .. (s12.south);
     \draw[-latex',thick,draw=black!40] (k12.north) .. controls +(north:0.5\hseg) and +(south:0.8\hseg) .. (s12.south);
@@ -63,11 +63,11 @@
 \node[attnnode,anchor=south] (attn13) at ([yshift=0.1\hnode]layer13.south) {};
 \node[anchor=north west,inner sep=4pt,font=\small] () at (attn13.north west) {注意力};
 \node[anchor=south,inner sep=0pt] (out13) at ([yshift=0.3\hseg]attn13.north) {$\cdots$};
-\node[thinnode,anchor=south west,thick,draw=dblue!40,text=black!40] (q13) at ([xshift=0.1\wseg,yshift=0.2\hseg]attn13.south west) {$Q^n$};
-\node[thinnode,anchor=south,thick,draw=orange!40,text=black!40] (k13) at ([yshift=0.2\hseg]attn13.south) {$K^n$};
-\node[thinnode,anchor=south east,thick,draw=purple!40,text=black!40] (v13) at ([xshift=-0.1\wseg,yshift=0.2\hseg]attn13.south east) {$V^n$};
-\node[fatnode,anchor=south,thick,draw=black!40,text=black!40] (s13) at ([xshift=0.5\wseg,yshift=0.8\hseg]q13.north east) {$S^n$};
-\node[fatnode,anchor=south,thick,densely dashed,draw] (a13) at ([xshift=0.45\wseg,yshift=1.3\hseg+0.6\hnode]k13.north east) {$A^n\!=\!A^m$};
+\node[thinnode,anchor=south west,thick,draw=dblue!40,text=black!40] (q13) at ([xshift=0.1\wseg,yshift=0.2\hseg]attn13.south west) {${\mathbi Q}^n$};
+\node[thinnode,anchor=south,thick,draw=orange!40,text=black!40] (k13) at ([yshift=0.2\hseg]attn13.south) {${\mathbi K}^n$};
+\node[thinnode,anchor=south east,thick,draw=purple!40,text=black!40] (v13) at ([xshift=-0.1\wseg,yshift=0.2\hseg]attn13.south east) {${\mathbi V}^n$};
+\node[fatnode,anchor=south,thick,draw=black!40,text=black!40] (s13) at ([xshift=0.5\wseg,yshift=0.8\hseg]q13.north east) {${\mathbi S}^n$};
+\node[fatnode,anchor=south,thick,densely dashed,draw] (a13) at ([xshift=0.45\wseg,yshift=1.3\hseg+0.6\hnode]k13.north east) {${\mathbi A}^n\!=\!{\mathbi A}^m$};
 \begin{scope}[fill=black!40]
     \draw[-latex',thick,draw=black!40] (q13.north) .. controls +(north:0.5\hseg) and +(south:0.8\hseg) .. (s13.south);
     \draw[-latex',thick,draw=black!40] (k13.north) .. controls +(north:0.5\hseg) and +(south:0.8\hseg) .. (s13.south);
@@ -87,11 +87,11 @@
         \node[anchor=north west,inner sep=4pt,font=\small] () at (attn\i\j.north west) {注意力};
         \node[anchor=south,inner sep=0pt] (out\i\j) at ([yshift=0.3\hseg]attn\i\j.north) {$\cdots$};
 
-        \node[thinnode,anchor=south west,thick,draw=dblue!\q,text=black] (q\i\j) at ([xshift=0.1\wseg,yshift=0.2\hseg]attn\i\j.south west) {$Q^m$};
-        \node[thinnode,anchor=south,thick,draw=orange!\q,text=black] (k\i\j) at ([yshift=0.2\hseg]attn\i\j.south) {$K^m$};
-        \node[thinnode,anchor=south east,thick,draw=purple!\s,text=black] (v\i\j) at ([xshift=-0.1\wseg,yshift=0.2\hseg]attn\i\j.south east) {$V^m$};
-        \node[fatnode,anchor=south,thick,draw=black!\s] (s\i\j) at ([xshift=0.45\wseg,yshift=0.8\hseg]q\i\j.north east) {$S^m\!=\!S(Q^m\!\cdot\!K^m)$};
-        \node[fatnode,anchor=south,thick,draw=black!80] (a\i\j) at ([xshift=0.45\wseg,yshift=1.3\hseg+0.6\hnode]k\i\j.north east) {$A^m\!=\!S^m\!\cdot\!V$};
+        \node[thinnode,anchor=south west,thick,draw=dblue!\q,text=black] (q\i\j) at ([xshift=0.1\wseg,yshift=0.2\hseg]attn\i\j.south west) {${\mathbi Q}^m$};
+        \node[thinnode,anchor=south,thick,draw=orange!\q,text=black] (k\i\j) at ([yshift=0.2\hseg]attn\i\j.south) {${\mathbi K}^m$};
+        \node[thinnode,anchor=south east,thick,draw=purple!\s,text=black] (v\i\j) at ([xshift=-0.1\wseg,yshift=0.2\hseg]attn\i\j.south east) {${\mathbi V}^m$};
+        \node[fatnode,anchor=south,thick,draw=black!\s] (s\i\j) at ([xshift=0.45\wseg,yshift=0.8\hseg]q\i\j.north east) {${\mathbi S}^m\!=\!{\mathbi S}({\mathbi Q}^m\!\cdot\!{\mathbi K}^m)$};
+        \node[fatnode,anchor=south,thick,draw=black!80] (a\i\j) at ([xshift=0.45\wseg,yshift=1.3\hseg+0.6\hnode]k\i\j.north east) {${\mathbi A}^m\!=\!{\mathbi S}^m\!\cdot\!{\mathbi V}$};
         \begin{scope}[fill=black!\q]
             \draw[-latex',thick,draw=black!\t] (q\i\j.north) .. controls +(north:0.5\hseg) and +(south:0.8\hseg) .. (s\i\j.south);
             \draw[-latex',thick,draw=black!\t] (k\i\j.north) .. controls +(north:0.5\hseg) and +(south:0.8\hseg) .. (s\i\j.south);