<?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 Deep Learning Adding More Training Data in Spatial Data Science Questions</title>
    <link>https://community.esri.com/t5/spatial-data-science-questions/deep-learning-adding-more-training-data/m-p/866266#M1817</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Is it possible to add more image chips to existing output folder from arcgis.learn.export_training_data? I currently have over 3000 chips in the folder that I've used to train my Single Shot Detector model. Now I have created another 1000+ chips (using the export training data function) that I want to continue training my existing model.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I've also tried to create a new Single Shot Detector with the new 1000+ training samples and use the .load method to load my existing trained model but get the following error message.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;IMG class="image-1 jive-image" height="610" src="https://community.esri.com/legacyfs/online/495356_pastedImage_1.png" width="735" /&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;What is the best way to training my existing model on the new training data? I'm having trouble finding resource&amp;nbsp; information besides the API reference and the basic notebook examples.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Thanks,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Ian&lt;/SPAN&gt;&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Wed, 03 Jun 2020 18:34:22 GMT</pubDate>
    <dc:creator>Anonymous User</dc:creator>
    <dc:date>2020-06-03T18:34:22Z</dc:date>
    <item>
      <title>Deep Learning Adding More Training Data</title>
      <link>https://community.esri.com/t5/spatial-data-science-questions/deep-learning-adding-more-training-data/m-p/866266#M1817</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Is it possible to add more image chips to existing output folder from arcgis.learn.export_training_data? I currently have over 3000 chips in the folder that I've used to train my Single Shot Detector model. Now I have created another 1000+ chips (using the export training data function) that I want to continue training my existing model.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I've also tried to create a new Single Shot Detector with the new 1000+ training samples and use the .load method to load my existing trained model but get the following error message.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;IMG class="image-1 jive-image" height="610" src="https://community.esri.com/legacyfs/online/495356_pastedImage_1.png" width="735" /&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;What is the best way to training my existing model on the new training data? I'm having trouble finding resource&amp;nbsp; information besides the API reference and the basic notebook examples.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Thanks,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Ian&lt;/SPAN&gt;&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 03 Jun 2020 18:34:22 GMT</pubDate>
      <guid>https://community.esri.com/t5/spatial-data-science-questions/deep-learning-adding-more-training-data/m-p/866266#M1817</guid>
      <dc:creator>Anonymous User</dc:creator>
      <dc:date>2020-06-03T18:34:22Z</dc:date>
    </item>
    <item>
      <title>Re: Deep Learning Adding More Training Data</title>
      <link>https://community.esri.com/t5/spatial-data-science-questions/deep-learning-adding-more-training-data/m-p/866267#M1818</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;There are samples on GitHub&lt;/P&gt;&lt;P&gt;&lt;A class="link-titled" href="https://github.com/Esri/arcgis-python-api/tree/master/samples" title="https://github.com/Esri/arcgis-python-api/tree/master/samples"&gt;arcgis-python-api/samples at master · Esri/arcgis-python-api · GitHub&lt;/A&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;and the api reference is here&lt;/P&gt;&lt;P&gt;&lt;A class="link-titled" href="https://developers.arcgis.com/python/api-reference/" title="https://developers.arcgis.com/python/api-reference/"&gt;API Reference for the ArcGIS API for Python — arcgis 1.8.0 documentation&lt;/A&gt;&amp;nbsp;&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 03 Jun 2020 19:45:44 GMT</pubDate>
      <guid>https://community.esri.com/t5/spatial-data-science-questions/deep-learning-adding-more-training-data/m-p/866267#M1818</guid>
      <dc:creator>DanPatterson</dc:creator>
      <dc:date>2020-06-03T19:45:44Z</dc:date>
    </item>
  </channel>
</rss>

