Skip to content

Commit 158db7a

Browse files
author
Jay Liu
authored
Update mnist_tf.md
1 parent 1efb47f commit 158db7a

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

SOURCE/tutorials/mnist_tf.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -81,7 +81,7 @@ labels_placeholder = tf.placeholder(tf.int32, shape=(batch_size))
8181

8282
`inference()`函数会尽可能地构建图表,做到返回包含了预测结果(output prediction)的Tensor。
8383

84-
它接受图像占位符为输入,在此基础上借助ReLu(Rectified Linear Units)激活函数,构建一对完全连接层(layers),以及一个有着十个节点(node)、指明了输出logtis模型的线性层
84+
它接受图像占位符为输入,在此基础上借助ReLu(Rectified Linear Units)激活函数,构建一对完全连接层(layers),以及一个有着十个节点(node)、指明了输出logits模型的线性层
8585

8686
每一层都创建于一个唯一的[`tf.name_scope`](../api_docs/python/framework.md#name_scope)之下,创建于该作用域之下的所有元素都将带有其前缀。
8787

@@ -397,4 +397,4 @@ print ' Num examples: %d Num correct: %d Precision @ 1: %0.02f' % (
397397

398398
> 原文:[TensorFlow Mechanics 101](http://www.tensorflow.org/tutorials/mnist/tf/index.md)
399399
> 翻译:[bingjin](https://github.com/bingjin)
400-
> 校对:[LichAmnesia](https://github.com/LichAmnesia)
400+
> 校对:[LichAmnesia](https://github.com/LichAmnesia)

0 commit comments

Comments
 (0)