<?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 eIQ tflite example for i.mx8mp in Generative AI &amp; LLMs</title>
    <link>https://community.nxp.com/t5/Generative-AI-LLMs/eIQ-tflite-example-for-i-mx8mp/m-p/2170681#M8</link>
    <description>&lt;P&gt;I am looking for a full tutorial that will show me how to get a ML model, convert it to tflite, load it to the NXP with a camera and display and run the model to detect objects. I am pretty positive the NXP I.MX8MP along with the eIQ toolkit should be able to do that, but so far I couldn't find any way to load and run a tflite model on the I.MX8MP.&amp;nbsp;&lt;/P&gt;&lt;P&gt;when trying to deploy any model, I am getting errors like "please check your vision pipeline settings and make sure your remote device is correctly set up!"&lt;/P&gt;&lt;P&gt;What does it mean?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Another thing that i am getting is this error when I am trying to run the gstreamer command the eIQ try to run. The error is&amp;nbsp;&lt;/P&gt;&lt;P&gt;** (gst-launch-1.0:2311): CRITICAL **: 18:16:43.063: _check_tensors: assertion 'config-&amp;gt;info.num_tensors &amp;gt;= limit' failed&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Again, incryptic message.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Help anyone?&lt;/P&gt;</description>
    <pubDate>Tue, 16 Sep 2025 21:19:44 GMT</pubDate>
    <dc:creator>zohargolan</dc:creator>
    <dc:date>2025-09-16T21:19:44Z</dc:date>
    <item>
      <title>eIQ tflite example for i.mx8mp</title>
      <link>https://community.nxp.com/t5/Generative-AI-LLMs/eIQ-tflite-example-for-i-mx8mp/m-p/2170681#M8</link>
      <description>&lt;P&gt;I am looking for a full tutorial that will show me how to get a ML model, convert it to tflite, load it to the NXP with a camera and display and run the model to detect objects. I am pretty positive the NXP I.MX8MP along with the eIQ toolkit should be able to do that, but so far I couldn't find any way to load and run a tflite model on the I.MX8MP.&amp;nbsp;&lt;/P&gt;&lt;P&gt;when trying to deploy any model, I am getting errors like "please check your vision pipeline settings and make sure your remote device is correctly set up!"&lt;/P&gt;&lt;P&gt;What does it mean?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Another thing that i am getting is this error when I am trying to run the gstreamer command the eIQ try to run. The error is&amp;nbsp;&lt;/P&gt;&lt;P&gt;** (gst-launch-1.0:2311): CRITICAL **: 18:16:43.063: _check_tensors: assertion 'config-&amp;gt;info.num_tensors &amp;gt;= limit' failed&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Again, incryptic message.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Help anyone?&lt;/P&gt;</description>
      <pubDate>Tue, 16 Sep 2025 21:19:44 GMT</pubDate>
      <guid>https://community.nxp.com/t5/Generative-AI-LLMs/eIQ-tflite-example-for-i-mx8mp/m-p/2170681#M8</guid>
      <dc:creator>zohargolan</dc:creator>
      <dc:date>2025-09-16T21:19:44Z</dc:date>
    </item>
  </channel>
</rss>

