<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Low Intersection over Union (mIOU) metric on Unet Classifier. in ArcGIS API for Python Questions</title>
    <link>https://community.esri.com/t5/arcgis-api-for-python-questions/low-intersection-over-union-miou-metric-on-unet/m-p/871032#M4660</link>
    <description>&lt;P&gt;Hello&lt;/P&gt;&lt;P&gt;I have replicated the code on this training example&lt;/P&gt;&lt;P&gt;&lt;A href="https://developers.arcgis.com/python/sample-notebooks/land-cover-classification-using-sparse-training-data/" target="_blank" rel="noopener"&gt;https://developers.arcgis.com/python/sample-notebooks/land-cover-classification-using-sparse-training-data/&lt;/A&gt;&lt;/P&gt;&lt;P&gt;And are interested in the F1 and mIOU metrics. The example shows F1 metrics which for me came out similar (but not exactly) to the example. They are all in the around 90 mark, all good.&amp;nbsp; My question is when, I run the mIOU score, the scores are 30 or less. Which would seem really low compared to F1.&amp;nbsp; Why are the mIOU scores so low?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Many thanks&lt;/P&gt;&lt;P&gt;I am running arcgis 1.8.2 and fastai 1.0.60&lt;/P&gt;</description>
    <pubDate>Fri, 13 Nov 2020 23:58:44 GMT</pubDate>
    <dc:creator>TimG</dc:creator>
    <dc:date>2020-11-13T23:58:44Z</dc:date>
    <item>
      <title>Low Intersection over Union (mIOU) metric on Unet Classifier.</title>
      <link>https://community.esri.com/t5/arcgis-api-for-python-questions/low-intersection-over-union-miou-metric-on-unet/m-p/871032#M4660</link>
      <description>&lt;P&gt;Hello&lt;/P&gt;&lt;P&gt;I have replicated the code on this training example&lt;/P&gt;&lt;P&gt;&lt;A href="https://developers.arcgis.com/python/sample-notebooks/land-cover-classification-using-sparse-training-data/" target="_blank" rel="noopener"&gt;https://developers.arcgis.com/python/sample-notebooks/land-cover-classification-using-sparse-training-data/&lt;/A&gt;&lt;/P&gt;&lt;P&gt;And are interested in the F1 and mIOU metrics. The example shows F1 metrics which for me came out similar (but not exactly) to the example. They are all in the around 90 mark, all good.&amp;nbsp; My question is when, I run the mIOU score, the scores are 30 or less. Which would seem really low compared to F1.&amp;nbsp; Why are the mIOU scores so low?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Many thanks&lt;/P&gt;&lt;P&gt;I am running arcgis 1.8.2 and fastai 1.0.60&lt;/P&gt;</description>
      <pubDate>Fri, 13 Nov 2020 23:58:44 GMT</pubDate>
      <guid>https://community.esri.com/t5/arcgis-api-for-python-questions/low-intersection-over-union-miou-metric-on-unet/m-p/871032#M4660</guid>
      <dc:creator>TimG</dc:creator>
      <dc:date>2020-11-13T23:58:44Z</dc:date>
    </item>
    <item>
      <title>Re: Low Intersection over Union (mIOU) metric on Unet Classifier.</title>
      <link>https://community.esri.com/t5/arcgis-api-for-python-questions/low-intersection-over-union-miou-metric-on-unet/m-p/1011660#M5356</link>
      <description>&lt;P&gt;Hey,&lt;/P&gt;&lt;P&gt;May I know the size of data you are using. Also, if you can share the results, data, and model you trained (if possible) it will help me further investigate the issue.&lt;/P&gt;</description>
      <pubDate>Tue, 22 Dec 2020 08:35:57 GMT</pubDate>
      <guid>https://community.esri.com/t5/arcgis-api-for-python-questions/low-intersection-over-union-miou-metric-on-unet/m-p/1011660#M5356</guid>
      <dc:creator>Anonymous User</dc:creator>
      <dc:date>2020-12-22T08:35:57Z</dc:date>
    </item>
  </channel>
</rss>

