<?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 Re: Can't export training data for deep learning as PNG chips in Geoprocessing Questions</title>
    <link>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/69792#M2496</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hi Philipp,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I had the same issue when trying to get an object-detection deep learning algorithm to run. I had a 16-bit unsigned orthomosaic with 5 bands. Following Makiko's advice on this thread, I extracted the first three bands (RGB bands), and then compiled them back into an orthomosaic using the "Composite" tool under "Raster Tools." After this, I exported the raster to my working directory as a TIFF file.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I then created my training samples, and exported them as PNG files. I was able to do this&amp;nbsp;with no problem.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;As I am using object detection, I exported them with the Meta&amp;nbsp;Data Format being "PASCAL Visual Object Classes," and it worked just fine.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Hope that helps!&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Thu, 03 Sep 2020 15:14:39 GMT</pubDate>
    <dc:creator>IsaacBarnhart</dc:creator>
    <dc:date>2020-09-03T15:14:39Z</dc:date>
    <item>
      <title>Can't export training data for deep learning as PNG chips</title>
      <link>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/69790#M2494</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;I want to use the ArcGIS Pro tool "Export training data for deep learning" on my raster, which has these properties:&lt;/P&gt;&lt;P&gt;&lt;IMG __jive_id="451541" class="image-1 jive-image" src="https://community.esri.com/legacyfs/online/451541_pastedImage_1.png" /&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I can't choose "png" as image format for the chips. it says error 001523 in the popup.&lt;/P&gt;&lt;P&gt;&lt;IMG __jive_id="451542" class="image-2 jive-image" src="https://community.esri.com/legacyfs/online/451542_pastedImage_7.png" /&gt;&lt;/P&gt;&lt;P&gt;&lt;A class="link-titled" href="https://pro.arcgis.com/en/pro-app/tool-reference/tool-errors-and-warnings/001001-010000/tool-errors-and-warnings-01501-01525-001523.htm" title="https://pro.arcgis.com/en/pro-app/tool-reference/tool-errors-and-warnings/001001-010000/tool-errors-and-warnings-01501-01525-001523.htm"&gt;001523: JPEG compression is only supported for 8-bit unsigned or 16-bit unsigned data with one or three bands and withou…&lt;/A&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I already tried converting it to a 16bit unsigned integer tiff WITHOUT compression. But it's the same error:&lt;/P&gt;&lt;P&gt;&lt;IMG class="image-3 jive-image" src="https://community.esri.com/legacyfs/online/451543_pastedImage_1.png" /&gt;&lt;/P&gt;&lt;P&gt;&lt;STRONG&gt;How do I prepare my raster, to be able to export chips as png? Why can't the tool do this for me automatically?&lt;/STRONG&gt;&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 26 Jun 2019 15:02:05 GMT</pubDate>
      <guid>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/69790#M2494</guid>
      <dc:creator>PhilippZacharias</dc:creator>
      <dc:date>2019-06-26T15:02:05Z</dc:date>
    </item>
    <item>
      <title>Re: Can't export training data for deep learning as PNG chips</title>
      <link>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/69791#M2495</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Have you tried input raster data to be 3 bands instead of using 4 bands?&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 17 Oct 2019 18:54:43 GMT</pubDate>
      <guid>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/69791#M2495</guid>
      <dc:creator>Anonymous User</dc:creator>
      <dc:date>2019-10-17T18:54:43Z</dc:date>
    </item>
    <item>
      <title>Re: Can't export training data for deep learning as PNG chips</title>
      <link>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/69792#M2496</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hi Philipp,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I had the same issue when trying to get an object-detection deep learning algorithm to run. I had a 16-bit unsigned orthomosaic with 5 bands. Following Makiko's advice on this thread, I extracted the first three bands (RGB bands), and then compiled them back into an orthomosaic using the "Composite" tool under "Raster Tools." After this, I exported the raster to my working directory as a TIFF file.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I then created my training samples, and exported them as PNG files. I was able to do this&amp;nbsp;with no problem.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;As I am using object detection, I exported them with the Meta&amp;nbsp;Data Format being "PASCAL Visual Object Classes," and it worked just fine.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Hope that helps!&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 03 Sep 2020 15:14:39 GMT</pubDate>
      <guid>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/69792#M2496</guid>
      <dc:creator>IsaacBarnhart</dc:creator>
      <dc:date>2020-09-03T15:14:39Z</dc:date>
    </item>
    <item>
      <title>Re: Can't export training data for deep learning as PNG chips</title>
      <link>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/1114634#M25976</link>
      <description>&lt;P&gt;Why not exporting tiles as .tif format? This would allow&amp;nbsp; to keep the 4 bands, and to train a Deep learning model on it.&lt;/P&gt;</description>
      <pubDate>Fri, 05 Nov 2021 19:40:37 GMT</pubDate>
      <guid>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/1114634#M25976</guid>
      <dc:creator>GLASCAMP</dc:creator>
      <dc:date>2021-11-05T19:40:37Z</dc:date>
    </item>
    <item>
      <title>Re: Can't export training data for deep learning as PNG chips</title>
      <link>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/1658389#M27640</link>
      <description>&lt;P&gt;Exporting training Data for deep learning , after creating samples, it has taken all my time and not finishing. In the review I only have images and labels, how long does it y'all&lt;/P&gt;</description>
      <pubDate>Thu, 16 Oct 2025 12:27:12 GMT</pubDate>
      <guid>https://community.esri.com/t5/geoprocessing-questions/can-t-export-training-data-for-deep-learning-as/m-p/1658389#M27640</guid>
      <dc:creator>NaomiNyasulu</dc:creator>
      <dc:date>2025-10-16T12:27:12Z</dc:date>
    </item>
  </channel>
</rss>

