Update c2s01_minist_beginners.tex

Author: terry182

tex_pdf/tutorials/c2s01_minist_beginners.tex

@@ -90,7 +90,7 @@
 
 Ⓔ \textcolor{etc}{The corresponding labels in MNIST are numbers between 0 and 9, describing which digit a given image is of. For the purposes of this tutorial, we're going to want our labels as "one-hot vectors". A one-hot vector is a vector which is 0 in most dimensions, and 1 in a single dimension. In this case, the $n$th digit will be represented as a vector which is 1 in the $n$th dimensions. For example, 3 would be $[0,0,0,1,0,0,0,0,0,0]$. Consequently, \lstinline{mnist.train.labels} is a \lstinline{[55000, 10]} array of floats.}
 
-Ⓒ 相对应的MNIST数据集的标签是介于0到9的数字，用来描述给定图片里表示的数字．为了用于这个教程，我们使标签数据是"one-hot vectors"． 一个one-hot向量除了某一位的数字是1以外其余各维度数字都是0．所以在此教程中，数字n将表示成一个只有在第$n$维度（从0开始）数字为1的10维向量．比如，标签0将表示成(\lstinline{[1,0,0,0,0,0,0,0,0,0,0]})．因此，\lstinline{mnist.train.labels}是一个 \lstinline{[55000, 10]} 的数字矩阵．
+Ⓒ 相对应的MNIST数据集的标签是介于0到9的数字，用来描述给定图片里表示的数字．为了用于这个教程，我们使标签数据是"one-hot vectors"． 一个one-hot向量除了某一位的数字是1以外其余各维度数字都是0．所以在此教程中，数字n将表示成一个只有在第$n$维度（从0开始）数字为1的10维向量．比如，标签3将表示成(\lstinline{[0,0,0,1,0,0,0,0,0,0]})．因此，\lstinline{mnist.train.labels}是一个 \lstinline{[55000, 10]} 的数字矩阵．
 
 \begin{figure}[htbp]
 \centering