From 07dca81ca89dbb9654902ff4208a29890582725c Mon Sep 17 00:00:00 2001 From: Andrew Erlichson Date: Fri, 8 Sep 2017 14:52:07 -0400 Subject: [PATCH] Corrected description of what padding SAME does (#12918) The description read that the padding=SAME adds zeros to the output tensor. It should say that it pads the input tensor. --- tensorflow/docs_src/tutorials/layers.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tensorflow/docs_src/tutorials/layers.md b/tensorflow/docs_src/tutorials/layers.md index 0815cc2a17b..8037c92c736 100644 --- a/tensorflow/docs_src/tutorials/layers.md +++ b/tensorflow/docs_src/tutorials/layers.md @@ -270,7 +270,7 @@ The `padding` argument specifies one of two enumerated values (case-insensitive): `valid` (default value) or `same`. To specify that the output tensor should have the same width and height values as the input tensor, we set `padding=same` here, which instructs TensorFlow to add 0 values to the -edges of the output tensor to preserve width and height of 28. (Without padding, +edges of the input tensor to preserve width and height of 28. (Without padding, a 5x5 convolution over a 28x28 tensor will produce a 24x24 tensor, as there are 24x24 locations to extract a 5x5 tile from a 28x28 grid.)