experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Corrected description of what padding SAME does (#12918)

Browse Source 
The description read that the padding=SAME adds zeros to the output tensor. It should say that it pads the input tensor.
This commit is contained in:
Andrew Erlichson 2017-09-08 14:52:07 -04:00 committed by Yifei Feng
parent 088a880ad6
commit 07dca81ca8
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tensorflow/docs_src/tutorials/layers.md
View File

@ -270,7 +270,7 @@ The `padding` argument specifies one of two enumerated values
(case-insensitive): `valid` (default value) or `same`. To specify that the (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, 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 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 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.) 24x24 locations to extract a 5x5 tile from a 28x28 grid.)