Update Transformer

Section06-Neural-Machine-Translation/section06.tex

@@ -2758,34 +2758,63 @@ $\textrm{``you''} = \argmax_{y} \textrm{P}(y|\textbf{s}_1, \alert{\textbf{C}})$
     \begin{itemize}
     \begin{itemize}
         \item 有了一个NMT模型，我们应该怎么使用梯度下降算法来训练一个翻译模型呢？ 或者说哪些因素会对RNN训练产生影响？
         \item 有了一个NMT模型，我们应该怎么使用梯度下降算法来训练一个翻译模型呢？ 或者说哪些因素会对RNN训练产生影响？
     \end{itemize}
     \end{itemize}
-    \begin{beamerboxesrounded}[upper=uppercolblue,lower=lowercolblue,shadow=true]{\small{\textbf{参数初始化}}}
-        {\footnotesize
-        \begin{spacing}{0.9}
-            给定模型结构，初始化的好坏决定了模型最后的性能。
-        \end{spacing}
-        }
-    \end{beamerboxesrounded}
-    \begin{beamerboxesrounded}[upper=uppercolblue,lower=lowercolblue,shadow=true]{\small{\textbf{优化器选择}}}
-        {\footnotesize
-        \begin{spacing}{0.9}
-            选择不同的优化器需要对使用的便利性与效果进行权衡。
-        \end{spacing}
-        }
-    \end{beamerboxesrounded}
-    \begin{beamerboxesrounded}[upper=uppercolblue,lower=lowercolblue,shadow=true]{\small{\textbf{学习率调度}}}
-        {\footnotesize
-        \begin{spacing}{0.9}
-            合适的学习率调度方案可以让训练过程又好又快。
-        \end{spacing}
-        }
-    \end{beamerboxesrounded}
-    \begin{beamerboxesrounded}[upper=uppercolblue,lower=lowercolblue,shadow=true]{\small{\textbf{多设备加速}}}
-        {\footnotesize
-        \begin{spacing}{0.9}
-            当训练非常缓慢的时候，可以使用多个设备并行计算加速。
-        \end{spacing}
-        }
-    \end{beamerboxesrounded}
+\begin{center}
+\begin{tikzpicture}
+\begin{scope}
+
+\node [anchor=south west,draw,inner sep=0.7em,minimum width=3em,fill=blue!20!white] (c1) at (0,0) {参数初始化};
+\node [anchor=north,draw,inner sep=0.7em,minimum width=3em,fill=yellow!20!white] (c2) at ([yshift=-1em]c1.south) {优化器选择};
+\node [anchor=north,draw,inner sep=0.7em,minimum width=3em,fill=red!20!white] (c3) at ([yshift=-1em]c2.south) {学习率调度};
+\node [anchor=north,draw,inner sep=0.7em,minimum width=3em,fill=ugreen!20!white] (c4) at ([yshift=-1em]c3.south) {多设备加速};
+
+
+
+\node [anchor=east] (line1) at ([xshift=-1.5em,yshift=0em]c1.west) {给定模型结构，初};
+\node [anchor=north west] (line2) at ([yshift=0.3em]line1.south west) {始化的好坏决定了};
+\node [anchor=north west] (line3) at ([yshift=0.3em]line2.south west) {模型最后的性能};
+
+
+\node [anchor=west] (line11) at ([xshift=1.5em,yshift=0em]c1.east) {选择不同的优化器};
+\node [anchor=north west] (line12) at ([yshift=0.3em]line11.south west) {需要对使用的便利};
+\node [anchor=north west] (line13) at ([yshift=0.3em]line12.south west) {性与效果进行权衡};
+
+
+\node [anchor=west] (line21) at ([yshift=-7em]line1.west) {合适的学习率调度};
+\node [anchor=north west] (line22) at ([yshift=0.3em]line21.south west) {方案可以让训练};
+\node [anchor=north west] (line23) at ([yshift=0.3em]line22.south west) {过程又好又快};
+
+
+\node [anchor=west] (line31) at ([yshift=-7em]line11.west) {当训练非常缓慢的};
+\node [anchor=north west] (line32) at ([yshift=0.3em]line31.south west) {时候，可以使用多};
+\node [anchor=north west] (line33) at ([yshift=0.3em]line32.south west) {设备并行计算加速};
+
+\draw [->,very thick] ([yshift=-0.1em]c1.south) -- ([yshift=0.1em]c2.north);
+\draw [->,very thick] ([yshift=-0.1em]c2.south) -- ([yshift=0.1em]c3.north);
+\draw [->,very thick] ([yshift=-0.1em]c3.south) -- ([yshift=0.1em]c4.north);
+
+\begin{pgfonlayer}{background}
+
+\node [rectangle,inner sep=0.2em,rounded corners=1pt,fill=blue!10,drop shadow,draw=blue] [fit = (line1) (line2) (line3)] (box1) {};
+\draw [->,dotted,very thick,blue] ([yshift=1.5em,xshift=1em]box1.east) -- ([yshift=1.5em,xshift=0.1em]box1.east);
+
+
+\node [rectangle,inner sep=0.2em,rounded corners=1pt,fill=yellow!20!white,drop shadow,draw=black] [fit = (line11) (line12) (line13)] (box2) {};
+\draw [->,dotted,very thick,black] ([yshift=-1.5em,xshift=-1em]box2.west) -- ([yshift=-1.5em,xshift=-0.1em]box2.west);
+
+
+\node [rectangle,inner sep=0.2em,rounded corners=1pt,fill=red!20,drop shadow,draw=red] [fit = (line21) (line22) (line23)] (box3) {};
+\draw [->,dotted,very thick,red] ([xshift=1em,yshift=1.5em]box3.east) -- ([xshift=0.1em,yshift=1.5em]box3.east) ;
+
+
+\node [rectangle,inner sep=0.2em,rounded corners=1pt,fill=ugreen!10,drop shadow,draw=ugreen] [fit = (line31) (line32) (line33)] (box4) {};
+\draw [->,dotted,very thick,ugreen] ([yshift=-1.5em,xshift=-1em]box4.west) -- ([yshift=-1.5em,xshift=-0.1em]box4.west);
+				
+\end{pgfonlayer}
+
+
+\end{scope}
+\end{tikzpicture}
+\end{center}
 \end{frame}
 \end{frame}
 
 
 \begin{frame}{训练 - 初始化}
 \begin{frame}{训练 - 初始化}