<br />I'm trying to make supervised land use classification map by using i.smap program.<br />So I run <span><span class="bold highlight search-highlight">i</span>.<span class="bold highlight search-highlight">gensigset</span> to make statistics for i.smap.<br /><br />But <span class="bold highlight search-highlight">I</span> had <span class="bold highlight search-highlight">errors</span>:
</span><br />------------------------------------------------<br /> > i.gensigset trainingmap=GT group=test sub=test signaturefile=sig<br /><br />Finding training classes...<br /> 100%<br />4 classes found<br />Reading raster maps...<br /> 100%<br />Clustering class 1 (396 pixels)...<br />WARNING: Removed a singular subsignature number 1 (9 remain)<br />WARNING: Removed a singular subsignature number 1 (8 remain)<br />WARNING: Removed a singular subsignature number 1 (7 remain)<br />WARNING: Removed a singular subsignature number 1 (6 remain)<br />WARNING: Removed a singular subsignature number 1 (5 remain)<br />WARNING: Removed a singular subsignature number 1 (4 remain)<br />WARNING: Removed a singular subsignature number 1 (3 remain)<br />WARNING: Removed a singular subsignature number 1 (2 remain)<br />WARNING: Removed a singular subsignature number 1 (1 remain)<br />WARNING: Unreliable clustering. Try a smaller initial number of
clusters<br />WARNING: Removed a singular subsignature number 1 (-1 remain)<br />WARNING: Unreliable clustering. Try a smaller initial number of clusters<br />Number of subclasses is 0<br />Clustering class 2 (36 pixels)...<br />WARNING: Too many subclasses for class index 2<br />Number of subclasses set to 4<br />WARNING: Removed a singular subsignature number 1 (3 remain)<br />WARNING: Removed a singular subsignature number 1 (2 remain)<br />WARNING: Removed a singular subsignature number 1 (1 remain)<br />WARNING: Unreliable clustering. Try a smaller initial number of clusters<br />WARNING: Removed a singular subsignature number 1 (-1 remain)<br />WARNING: Unreliable clustering. Try a smaller initial number of clusters<br />Number of subclasses is 0<br />Clustering class 3 (99 pixels)...<br />WARNING: Removed a singular subsignature number 1 (9 remain)<br />WARNING: Removed a singular subsignature number 1 (8 remain)<br />WARNING: Removed a singular
subsignature number 1 (7 remain)<br />WARNING: Removed a singular subsignature number 1 (6 remain)<br />WARNING: Removed a singular subsignature number 1 (5 remain)<br />WARNING: Removed a singular subsignature number 1 (4 remain)<br />WARNING: Removed a singular subsignature number 1 (3 remain)<br />WARNING: Removed a singular subsignature number 1 (2 remain)<br />WARNING: Removed a singular subsignature number 1 (1 remain)<br />WARNING: Unreliable clustering. Try a smaller initial number of clusters<br />WARNING: Removed a singular subsignature number 1 (-1 remain)<br />WARNING: Unreliable clustering. Try a smaller initial number of clusters<br />Number of subclasses is 0<br />Clustering class 4 (9 pixels)...<br />WARNING: Not enough pixels in class 4<br />Number of subclasses is 0<br />i.gensigset complete.<br />----------------------------<br /><br />I tried to solve the errors:<br />
1. Changed null data to 0.<br />
2. Enlarge training area <br />
<br />But I can't solve the errros.<br />Why I had these errors? What should I do to solve the errors?<br />Thanks<br /><br />Kei<br />