<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html; charset=ISO-8859-15"
http-equiv="Content-Type">
</head>
<body text="#000000" bgcolor="#ffffff">
Hello Natalia:<br>
<br>
(Returning to the list - perhaps someone else can help also)<br>
<br>
<br>
On 11/05/2010 03:20 PM, Sofina Natalia wrote:
<blockquote cite="mid:4CD4049B.6020009@gmx.de" type="cite">
<meta content="text/html; charset=ISO-8859-15"
http-equiv="Content-Type">
Am 04.11.2010 20:20, schrieb Micha Silver:
<blockquote cite="mid:4CD3077B.8040600@arava.co.il" type="cite"><br>
The "too many subclasses" is not necessarily an error. I believe that
it means one classification is too complicated, that is the spread of
pixel values is such that it can't create a signature for that class. <br>
Did the process finish? <br>
How did you make the training map? Are all the training areas with the
same category uniform? If you setup a training area that is too large,
with a broad mix of pixel values, then gensigset won't be able to
create unique signatures for each class. <br>
HTH <br>
<br>
--------------------------------------------------------------------------------------------</blockquote>
<meta http-equiv="CONTENT-TYPE"
content="text/html; charset=ISO-8859-15">
<title></title>
<meta name="GENERATOR" content="OpenOffice.org 3.2 (Win32)">
<style type="text/css">
<!--
@page { margin: 2cm }
P { margin-bottom: 0.21cm }
-->
</style>
<p style="margin-bottom: 0cm;">Hi, Micha!</p>
I can't create a “sig-file”
still... Below it is what I got after starting the i.gensigset:
<p style="margin-bottom: 0cm;">---------------------------------------------------------------------------------------------------------------</p>
<p style="margin-bottom: 0cm;">(Fri Nov 05 12:47:14 2010) </p>
<p style="margin-bottom: 0cm;">i.gensigset
trainingmap=my_cl@image_classification
group=train@image_classification subgroup=train_sub
signaturefile=train_sig</p>
</blockquote>
<br>
No need to explicitly enter the mapset here. It shoud be enough to do:<br>
i.gensigset
trainingmap=my_cl
group=train \ <br>
subgroup=train_sub
signaturefile=train_sig<br>
<br>
<blockquote cite="mid:4CD4049B.6020009@gmx.de" type="cite">
<p style="margin-bottom: 0cm;">Finding training classes...</p>
<p style="margin-bottom: 0cm;">6 classes found</p>
<p style="margin-bottom: 0cm;">Reading raster maps...</p>
<p style="margin-bottom: 0cm;">Clustering class 1 (3324 pixels)...</p>
<p style="margin-bottom: 0cm;">Removed a singular subsignature number
5 (9 remain)</p>
<p style="margin-bottom: 0cm;">Removed a singular subsignature number
8 (8 remain)</p>
<p style="margin-bottom: 0cm;">Number of subclasses is 6</p>
<p style="margin-bottom: 0cm;">Clustering class 2 (1898 pixels)...</p>
<p style="margin-bottom: 0cm;">Removed a singular subsignature number
9 (9 remain)</p>
<p style="margin-bottom: 0cm;">Number of subclasses is 3</p>
<p style="margin-bottom: 0cm;">Clustering class 3 (2710 pixels)...</p>
<p style="margin-bottom: 0cm;">Number of subclasses is 10</p>
<p style="margin-bottom: 0cm;">Clustering class 4 (1347 pixels)...</p>
<p style="margin-bottom: 0cm;">Removed a singular subsignature number
10 (9 remain)</p>
<p style="margin-bottom: 0cm;">Removed a singular subsignature number
6 (8 remain)</p>
<p style="margin-bottom: 0cm;">Removed a singular subsignature number
2 (7 remain)</p>
<p style="margin-bottom: 0cm;">Number of subclasses is 6</p>
<p style="margin-bottom: 0cm;">Clustering class 5 (1024 pixels)...</p>
<p style="margin-bottom: 0cm;">Number of subclasses is 4</p>
<p style="margin-bottom: 0cm;">Clustering class 6 (2107 pixels)...</p>
<p style="margin-bottom: 0cm;">Number of subclasses is 1</p>
</blockquote>
<br>
So far this looks normal. You have a few thousand pixels in each
training area which should be enough.<br>
<br>
<blockquote cite="mid:4CD4049B.6020009@gmx.de" type="cite">
<p style="margin-bottom: 0cm;">unable to create signature file
train_sig for subgroup train_sub of group train@image_classification</p>
</blockquote>
<br>
Hmmm... What went wrong? One additional test below...<br>
<br>
<blockquote cite="mid:4CD4049B.6020009@gmx.de" type="cite">
<p style="margin-bottom: 0cm;">ERROR: Unable to create signature file
<train_sig></p>
<p
style="border-style: none none solid; border-color: -moz-use-text-color -moz-use-text-color rgb(0, 0, 0); border-width: medium medium 1px; padding: 0cm 0cm 0.07cm; margin-bottom: 0cm;">
(Fri Nov 05 12:47:19 2010) Command finished (5 sec) </p>
<p style="margin-bottom: 0cm;"><br>
</p>
<p style="margin-bottom: 0cm;">My training map I make so as it is
described in your paper. I've tried to create it with different sizes
of the training areas. And the color of the area I define using the
function r.what.color.</p>
</blockquote>
<br>
I'm not sure what you mean here. Each training area should cover a
uniform feature in the landscape. Perhaps send the output of:<br>
r.info my_cl<br>
r.univar my_cl<br>
<br>
<br>
<blockquote cite="mid:4CD4049B.6020009@gmx.de" type="cite">I don't
understand what is wrong...
Which size should be a training area? Does it depend on the number of
pixels?
<p style="margin-bottom: 0cm;">Thanks a lot,</p>
<p style="margin-bottom: 0cm;">Natalia</p>
<br>
<br>
This mail was received via Mail-SeCure System.<br>
</blockquote>
<br>
<br>
<pre class="moz-signature" cols="72">--
Micha Silver
Arava Development Co. +972-52-3665918
<a class="moz-txt-link-freetext" href="http://www.surfaces.co.il">http://www.surfaces.co.il</a>
</pre>
</body>
</html>