<?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 How to specify VsiNpu as Computational Backend  for a custom built C/C++ application on NXP i.MX8 in eIQ Machine Learning Software</title>
    <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/How-to-specify-VsiNpu-as-Computational-Backend-for-a-custom/m-p/1300413#M376</link>
    <description>&lt;P&gt;Hi,&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp;I am trying to execute a custom built C++ application using ARMNN on i.MX8. How to specify it to use VsiNpu&amp;nbsp;as the backend for Computation. Currently it works with CpuAcc Backend where this is specified when creating the context for a specific compute device.&lt;/P&gt;&lt;P&gt;Thanks &amp;amp; Regards,&lt;/P&gt;&lt;P&gt;Divya&lt;/P&gt;&lt;P&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Wed, 30 Jun 2021 12:31:11 GMT</pubDate>
    <dc:creator>Divya17</dc:creator>
    <dc:date>2021-06-30T12:31:11Z</dc:date>
    <item>
      <title>How to specify VsiNpu as Computational Backend  for a custom built C/C++ application on NXP i.MX8</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/How-to-specify-VsiNpu-as-Computational-Backend-for-a-custom/m-p/1300413#M376</link>
      <description>&lt;P&gt;Hi,&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp;I am trying to execute a custom built C++ application using ARMNN on i.MX8. How to specify it to use VsiNpu&amp;nbsp;as the backend for Computation. Currently it works with CpuAcc Backend where this is specified when creating the context for a specific compute device.&lt;/P&gt;&lt;P&gt;Thanks &amp;amp; Regards,&lt;/P&gt;&lt;P&gt;Divya&lt;/P&gt;&lt;P&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Wed, 30 Jun 2021 12:31:11 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/How-to-specify-VsiNpu-as-Computational-Backend-for-a-custom/m-p/1300413#M376</guid>
      <dc:creator>Divya17</dc:creator>
      <dc:date>2021-06-30T12:31:11Z</dc:date>
    </item>
    <item>
      <title>Re: How to specify VsiNpu as Computational Backend  for a custom built C/C++ application on NXP i.MX</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/How-to-specify-VsiNpu-as-Computational-Backend-for-a-custom/m-p/1381369#M573</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;&lt;P&gt;It seems you choose the backend like this (for VsiNpu) before loading the network :&lt;/P&gt;&lt;P&gt;&lt;FONT face="courier new,courier"&gt;armnn::IOptimizedNetworkPtr optNet = armnn::Optimize(*network, {armnn::Compute::VsiNpu}, runtime-&amp;gt;GetDeviceSpec());&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;Regards&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 03 Dec 2021 18:17:30 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/How-to-specify-VsiNpu-as-Computational-Backend-for-a-custom/m-p/1381369#M573</guid>
      <dc:creator>mbrundler</dc:creator>
      <dc:date>2021-12-03T18:17:30Z</dc:date>
    </item>
  </channel>
</rss>

