[pktools] 05/15: Add man page for pkregann.
Bas Couwenberg
sebastic at xs4all.nl
Fri Dec 12 16:05:18 UTC 2014
This is an automated email from the git hooks/post-receive script.
sebastic-guest pushed a commit to branch master
in repository pktools.
commit e3f904bc67cd050586851ddcf3312d1b97c831de
Author: Bas Couwenberg <sebastic at xs4all.nl>
Date: Thu Dec 11 23:46:52 2014 +0100
Add man page for pkregann.
---
debian/changelog | 2 +-
debian/man/pkregann.1.xml | 220 ++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 221 insertions(+), 1 deletion(-)
diff --git a/debian/changelog b/debian/changelog
index db8d84a..55c8387 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -6,7 +6,7 @@ pktools (2.6.1-1) UNRELEASED; urgency=medium
* Add man page for pkann, pkascii2img, pkascii2ogr, pkcomposite, pkcreatect,
pkcrop, pkdiff, pkdsm2shadow, pkdumpimg, pkdumpogr, pkegcs, pkextract,
pkfillnodata, pkfilter, pkfilterascii, pkfilterdem, pkfsann, pkfssvm,
- pkgetmask, pkinfo, pklas2img, pkoptsvm, pkpolygonize.
+ pkgetmask, pkinfo, pklas2img, pkoptsvm, pkpolygonize, pkregann.
-- Bas Couwenberg <sebastic at xs4all.nl> Wed, 03 Dec 2014 21:16:31 +0100
diff --git a/debian/man/pkregann.1.xml b/debian/man/pkregann.1.xml
new file mode 100644
index 0000000..559880d
--- /dev/null
+++ b/debian/man/pkregann.1.xml
@@ -0,0 +1,220 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN" "http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd">
+<refentry id='pkregann'>
+
+ <refmeta>
+ <refentrytitle>pkregann</refentrytitle>
+ <manvolnum>1</manvolnum>
+ </refmeta>
+
+ <refnamediv>
+ <refname>pkregann</refname>
+ <refpurpose>regression with artificial neural network (multi-layer perceptron)</refpurpose>
+ </refnamediv>
+
+ <refsynopsisdiv id='synopsis'>
+ <cmdsynopsis>
+ <command>pkregann</command>
+ <arg choice='plain'><option>-i</option> <replaceable>input</replaceable></arg>
+ <arg choice='plain'><option>-t</option> <replaceable>training</replaceable></arg>
+ <arg choice='opt'><option>-ic</option> <replaceable>col</replaceable></arg>
+ <arg choice='opt'><option>-oc</option> <replaceable>col</replaceable></arg>
+ <arg choice='plain'><option>-o</option> <replaceable>output</replaceable></arg>
+ <arg choice='opt'><replaceable>options</replaceable></arg>
+ <arg choice='opt'><replaceable>advanced options</replaceable></arg>
+ </cmdsynopsis>
+ </refsynopsisdiv>
+
+ <refsect1 id='description'>
+ <title>DESCRIPTION</title>
+ <para>
+ <command>pkregann</command> performs a regression based on an artificial
+ neural network.
+ The regression is trained from the input (<option>-ic</option>) and
+ output (<option>-oc</option>) columns in a training text file.
+ Each row in the training file represents one sampling unit.
+ Multi-dimensional input features can be defined with multiple input
+ options (e.g.,
+ <option>-ic</option> <replaceable>0</replaceable>
+ <option>-ic</option> <replaceable>1</replaceable>
+ <option>-ic</option> <replaceable>2</replaceable>
+ for three dimensional features).
+ </para>
+ </refsect1>
+
+ <refsect1 id='options'>
+ <title>OPTIONS</title>
+ <variablelist>
+
+ <varlistentry>
+ <term><option>-i</option> <replaceable>filename</replaceable></term>
+ <term><option>--input</option> <replaceable>filename</replaceable></term>
+ <listitem>
+ <para>
+ input ASCII file
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-t</option> <replaceable>filename</replaceable></term>
+ <term><option>--training</option> <replaceable>filename</replaceable></term>
+ <listitem>
+ <para>
+ training ASCII file (each row represents one sampling unit.
+ Input features should be provided as columns, followed by output)
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-o</option> <replaceable>filename</replaceable></term>
+ <term><option>--output</option> <replaceable>filename</replaceable></term>
+ <listitem>
+ <para>
+ output ASCII file for result
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-ic</option> <replaceable>col</replaceable></term>
+ <term><option>--inputCols</option> <replaceable>col</replaceable></term>
+ <listitem>
+ <para>
+ input columns (e.g., for three dimensional input data in first
+ three columns use:
+ <option>-ic</option> <replaceable>0</replaceable>
+ <option>-ic</option> <replaceable>1</replaceable>
+ <option>-ic</option> <replaceable>2</replaceable>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-oc</option> <replaceable>col</replaceable></term>
+ <term><option>--outputCols</option> <replaceable>col</replaceable></term>
+ <listitem>
+ <para>
+ output columns (e.g., for two dimensional output in columns 3 and 4
+ (starting from <replaceable>0</replaceable>) use:
+ <option>-oc</option> <replaceable>3</replaceable>
+ <option>-oc</option> <replaceable>4</replaceable>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-from</option> <replaceable>row</replaceable></term>
+ <term><option>--from</option> <replaceable>row</replaceable></term>
+ <listitem>
+ <para>
+ start from this row in training file (start from 0)
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-to</option> <replaceable>row</replaceable></term>
+ <term><option>--to</option> <replaceable>row</replaceable></term>
+ <listitem>
+ <para>
+ read until this row in training file (start from 0 or set leave 0
+ as default to read until end of file)
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-cv</option> <replaceable>size</replaceable></term>
+ <term><option>--cv</option> <replaceable>size</replaceable></term>
+ <listitem>
+ <para>
+ n-fold cross validation mode
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-nn</option> <replaceable>number</replaceable></term>
+ <term><option>--nneuron</option> <replaceable>number</replaceable></term>
+ <listitem>
+ <para>
+ number of neurons in hidden layers in neural network (multiple
+ hidden layers are set by defining multiple number of neurons:
+ <option>-n</option> <replaceable>15</replaceable>
+ <option>-n</option> <replaceable>1</replaceable>,
+ default is one hidden layer with 5 neurons)
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-v</option> <replaceable>level</replaceable></term>
+ <term><option>--verbose</option> <replaceable>level</replaceable></term>
+ <listitem>
+ <para>
+ set to: 0 (results only), 1 (confusion matrix), 2 (debug)
+ </para>
+ </listitem>
+ </varlistentry>
+
+ </variablelist>
+
+ <para>Advanced options</para>
+ <variablelist>
+
+ <varlistentry>
+ <term><option>--offset</option> <replaceable>value</replaceable></term>
+ <listitem>
+ <para>
+ offset value for each spectral band input features:
+ refl[band]=(DN[band]-offset[band])/scale[band]
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>--scale</option> <replaceable>value</replaceable></term>
+ <listitem>
+ <para>
+ scale value for each spectral band input features:
+ refl=(DN[band]-offset[band])/scaleband
+ (use 0 if scale min and max in each band to -1.0 and 1.0)
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>--connection</option> <replaceable>rate</replaceable></term>
+ <listitem>
+ <para>
+ connection rate (default: 1.0 for a fully connected network)
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-l</option> <replaceable>rate</replaceable></term>
+ <term><option>--learning</option> <replaceable>rate</replaceable></term>
+ <listitem>
+ <para>
+ learning rate (default: 0.7)
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>--maxit</option> <replaceable>number</replaceable></term>
+ <listitem>
+ <para>
+ number of maximum iterations (epoch) (default: 500)
+ </para>
+ </listitem>
+ </varlistentry>
+
+ </variablelist>
+
+ </refsect1>
+
+</refentry>
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/pkg-grass/pktools.git
More information about the Pkg-grass-devel
mailing list