<?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: Understanding performance for Go-point demos in i.MX Processors</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/Understanding-performance-for-Go-point-demos/m-p/2128766#M239007</link>
    <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/251378"&gt;@ashwanipal01&lt;/a&gt;!&lt;/P&gt;
&lt;P&gt;Thank you for reaching out to NXP Support!&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The i.MX8MP is capable of supporting 4K resolution at 30fps.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;It’s possible that the NPU is not being utilized for inference tasks in your current setup. Please ensure that the NPU is properly enabled and integrated into your pipeline to achieve optimal performance.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Best regards,&lt;BR /&gt;Chavira&lt;/P&gt;</description>
    <pubDate>Fri, 04 Jul 2025 18:05:30 GMT</pubDate>
    <dc:creator>Chavira</dc:creator>
    <dc:date>2025-07-04T18:05:30Z</dc:date>
    <item>
      <title>Understanding performance for Go-point demos</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Understanding-performance-for-Go-point-demos/m-p/2128669#M238997</link>
      <description>&lt;P&gt;Please help me with the following Question related to the expected performance of detection models like Mobilenetssdv2:&lt;/P&gt;&lt;OL&gt;&lt;LI&gt;I am currently following the GitHub Link for understanding the performance of the detection models used in the Go point demo on my IMX8MP hardware.&lt;A href="https://github.com/nxp-imx-support/nxp-demo-experience-demos-list/tree/lf-6.12.3_1.0.0/scripts/machine_learning/nnstreamer/detection" target="_self"&gt;&amp;nbsp;Click here&lt;/A&gt;&lt;/LI&gt;&lt;LI&gt;I could understand that the demonstrations are only for &amp;lt;=480P quality videos.&lt;/LI&gt;&lt;LI&gt;Is there any sample in which IMX8MP can reach a greater than 20FPS for higher video resolution, like 720p and 1080p. Please share&lt;/LI&gt;&lt;LI&gt;I am assuming that this hardware can only achieve 20 FPS for &amp;lt;=480P videos for a detection model like mobilenetssdv2. Please suggest if you have any information on this.&lt;/LI&gt;&lt;LI&gt;BSP version is 5.15.52 krikstone&lt;/LI&gt;&lt;/OL&gt;&lt;P&gt;Thanks&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 04 Jul 2025 12:22:18 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Understanding-performance-for-Go-point-demos/m-p/2128669#M238997</guid>
      <dc:creator>ashwanipal01</dc:creator>
      <dc:date>2025-07-04T12:22:18Z</dc:date>
    </item>
    <item>
      <title>Re: Understanding performance for Go-point demos</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Understanding-performance-for-Go-point-demos/m-p/2128766#M239007</link>
      <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/251378"&gt;@ashwanipal01&lt;/a&gt;!&lt;/P&gt;
&lt;P&gt;Thank you for reaching out to NXP Support!&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The i.MX8MP is capable of supporting 4K resolution at 30fps.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;It’s possible that the NPU is not being utilized for inference tasks in your current setup. Please ensure that the NPU is properly enabled and integrated into your pipeline to achieve optimal performance.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Best regards,&lt;BR /&gt;Chavira&lt;/P&gt;</description>
      <pubDate>Fri, 04 Jul 2025 18:05:30 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Understanding-performance-for-Go-point-demos/m-p/2128766#M239007</guid>
      <dc:creator>Chavira</dc:creator>
      <dc:date>2025-07-04T18:05:30Z</dc:date>
    </item>
  </channel>
</rss>

