Merge pull request #1061 from ibmua/patch-3

Clearer explanation of padding

1 files changed, 18 insertions, 19 deletions

diff --git a/doc/convolution.md b/doc/convolution.md
index c96644b..96979ac 100644
--- a/doc/convolution.md
+++ b/doc/convolution.md
@@ -345,8 +345,8 @@ The parameters are the following:
   * `kH`: The kernel height of the convolution
   * `dW`: The step of the convolution in the width dimension. Default is `1`.
   * `dH`: The step of the convolution in the height dimension. Default is `1`.
-  * `padW`: The additional zeros added per width to the input planes. Default is `0`, a good number is `(kW-1)/2`.
-  * `padH`: The additional zeros added per height to the input planes. Default is `padW`, a good number is `(kH-1)/2`.
+  * `padW`: Additional zeros added to the input plane data on both sides of width axis. Default is `0`. `(kW-1)/2` is often used here.
+  * `padH`: Additional zeros added to the input plane data on both sides of height axis. Default is `0`. `(kH-1)/2` is often used here.
 
 Note that depending of the size of your kernel, several (of the last)
 columns or rows of the input image might be lost. It is up to the user to
@@ -438,8 +438,8 @@ The parameters are the following:
   * `kH`: The kernel height of the convolution
   * `dW`: The step of the convolution in the width dimension. Default is `1`.
   * `dH`: The step of the convolution in the height dimension. Default is `1`.
-  * `padW`: The additional zeros added per width to the input planes. Default is `0`, a good number is `(kW-1)/2`.
-  * `padH`: The additional zeros added per height to the input planes. Default is `0`, a good number is `(kH-1)/2`.
+  * `padW`: Additional zeros added to the input plane data on both sides of width axis. Default is `0`. `(kW-1)/2` is often used here.
+  * `padH`: Additional zeros added to the input plane data on both sides of height axis. Default is `0`. `(kH-1)/2` is often used here.
   * `adjW`: Extra width to add to the output image. Default is `0`. Cannot be greater than dW-1.
   * `adjH`: Extra height to add to the output image. Default is `0`. Cannot be greater than dH-1.
 
@@ -470,8 +470,8 @@ The parameters are the following:
   * `kH`: The kernel height of the convolution
   * `dW`: The step of the convolution in the width dimension. Default is `1`.
   * `dH`: The step of the convolution in the height dimension. Default is `1`.
-  * `padW`: The additional zeros added per width to the input planes. Default is `0`, a good number is `(kW-1)/2`.
-  * `padH`: The additional zeros added per height to the input planes. Default is `0`, a good number is `(kH-1)/2`.
+  * `padW`: Additional zeros added to the input plane data on both sides of width axis. Default is `0`. `(kW-1)/2` is often used here.
+  * `padH`: Additional zeros added to the input plane data on both sides of height axis. Default is `0`. `(kH-1)/2` is often used here.
   * `dilationW`: The number of pixels to skip. Default is `1`. `1` makes it a SpatialConvolution
   * `dilationH`: The number of pixels to skip. Default is `1`. `1` makes it a SpatialConvolution
 
@@ -505,8 +505,8 @@ The parameters are the following:
   * `kH`: The kernel height.
   * `dW`: The step in the width dimension. Default is `1`.
   * `dH`: The step in the height dimension. Default is `1`.
-  * `padW`: The additional zeros added per width to the input planes. Default is `0`, a good number is `(kW-1)/2`.
-  * `padH`: The additional zeros added per height to the input planes. Default is `0`, a good number is `(kH-1)/2`.
+  * `padW`: Additional zeros added to the input plane data on both sides of width axis. Default is `0`.
+  * `padH`: Additional zeros added to the input plane data on both sides of height axis. Default is `0`.
 
 If the input image is a 3D tensor `nInputPlane x iH x iW`, the output image size
 will be `nOutputPlane x oH x oW` where
@@ -923,11 +923,10 @@ The parameters are the following:
   * `dT`: The step of the convolution in the time dimension. Default is `1`.
   * `dW`: The step of the convolution in the width dimension. Default is `1`.
   * `dH`: The step of the convolution in the height dimension. Default is `1`.
-  * `padT`: The additional zeros added per time to the input planes. Default is `0`, a good number is `(kT-1)/2`.
-  * `padW`: The additional zeros added per width to the input planes. Default is `0`, a good number is `(kW-1)/2`.
-  * `padH`: The additional zeros added per height to the input planes. Default is `0`, a good number is `(kH-1)/2`.
-
-
+  * `padT`: Additional zeros added to the input plane data on both sides of time axis. Default is `0`. `(kT-1)/2` is often used here.
+  * `padW`: Additional zeros added to the input plane data on both sides of width axis. Default is `0`. `(kW-1)/2` is often used here.
+  * `padH`: Additional zeros added to the input plane data on both sides of height axis. Default is `0`. `(kH-1)/2` is often used here.
+  
 Note that depending of the size of your kernel, several (of the last)
 columns or rows of the input image might be lost. It is up to the user to
 add proper padding in images.
@@ -967,9 +966,9 @@ The parameters are the following:
 * `dT`: The step of the convolution in the depth dimension. Default is `1`.
 * `dW`: The step of the convolution in the width dimension. Default is `1`.
 * `dH`: The step of the convolution in the height dimension. Default is `1`.
-* `padT`: The additional zeros added per depth to the input planes. Default is `0`, a good number is `(kT-1)/2`.
-* `padW`: The additional zeros added per width to the input planes. Default is `0`, a good number is `(kW-1)/2`.
-* `padH`: The additional zeros added per height to the input planes. Default is `0`, a good number is `(kH-1)/2`.
+* `padT`: Additional zeros added to the input plane data on both sides of time (depth) axis. Default is `0`. `(kT-1)/2` is often used here.
+* `padW`: Additional zeros added to the input plane data on both sides of width axis. Default is `0`. `(kW-1)/2` is often used here.
+* `padH`: Additional zeros added to the input plane data on both sides of height axis. Default is `0`. `(kH-1)/2` is often used here.
 
 If the input image is a 3D tensor `nInputPlane x depth x height x width`, the output image size
 will be `nOutputPlane x odepth x oheight x owidth` where
@@ -998,9 +997,9 @@ The parameters are the following:
   * `dT`: The step of the convolution in the depth dimension. Default is `1`.
   * `dW`: The step of the convolution in the width dimension. Default is `1`.
   * `dH`: The step of the convolution in the height dimension. Default is `1`.
-  * `padT`: The additional zeros added per depth to the input planes. Default is `0`, a good number is `(kT-1)/2`.
-  * `padW`: The additional zeros added per width to the input planes. Default is `0`, a good number is `(kW-1)/2`.
-  * `padH`: The additional zeros added per height to the input planes. Default is `0`, a good number is `(kH-1)/2`.
+  * `padT`: Additional zeros added to the input plane data on both sides of time (depth) axis. Default is `0`. `(kT-1)/2` is often used here.
+  * `padW`: Additional zeros added to the input plane data on both sides of width axis. Default is `0`. `(kW-1)/2` is often used here.
+  * `padH`: Additional zeros added to the input plane data on both sides of height axis. Default is `0`. `(kH-1)/2` is often used here.
   * `dilationT`: The number of pixels to skip. Default is `1`. `1` makes it a VolumetricConvolution
   * `dilationW`: The number of pixels to skip. Default is `1`. `1` makes it a VolumetricConvolution
   * `dilationH`: The number of pixels to skip. Default is `1`. `1` makes it a VolumetricConvolution