<?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>i.MX Processors中的主题 Re: xnnpack in tensorflow lite for imx8 plus</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/xnnpack-in-tensorflow-lite-for-imx8-plus/m-p/1288345#M175128</link>
    <description>&lt;P&gt;Hi ,&amp;nbsp;&lt;/P&gt;&lt;P&gt;thanks for reply .&lt;/P&gt;&lt;P&gt;1. Where can I find tensorflow lite prebuild library.&lt;/P&gt;&lt;P&gt;2.Does this prebuild library will also support IMX8 plus NPU delegate ?&lt;/P&gt;&lt;P&gt;3.We building all our libraries as part of image yocto recipe build , is there recipe with tensorflow branch with NNAPI and XNNPack for NPU/CPU ?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;thanks&lt;/P&gt;</description>
    <pubDate>Mon, 07 Jun 2021 13:44:14 GMT</pubDate>
    <dc:creator>dnozik</dc:creator>
    <dc:date>2021-06-07T13:44:14Z</dc:date>
    <item>
      <title>xnnpack in tensorflow lite for imx8 plus</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/xnnpack-in-tensorflow-lite-for-imx8-plus/m-p/1288268#M175117</link>
      <description>&lt;P&gt;Hi ,&lt;/P&gt;&lt;P&gt;I working on&amp;nbsp;&lt;SPAN&gt;&amp;nbsp;Imx8 plus board. (zeus-5.4.70-2.3.0).&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;I trying to execute my models with Tensorflow Lite (version&amp;nbsp; imx_5.4.70_2.3.0 ) via XNNPack delegate. looks like in Makefile there is default value&amp;nbsp; CXXFLAGS += -DTFLITE_WITHOUT_XNNPACK&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Is there a reason XNNPack disabled? &lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Mon, 07 Jun 2021 12:00:53 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/xnnpack-in-tensorflow-lite-for-imx8-plus/m-p/1288268#M175117</guid>
      <dc:creator>dnozik</dc:creator>
      <dc:date>2021-06-07T12:00:53Z</dc:date>
    </item>
    <item>
      <title>Re: xnnpack in tensorflow lite for imx8 plus</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/xnnpack-in-tensorflow-lite-for-imx8-plus/m-p/1288317#M175124</link>
      <description>&lt;P&gt;Hello dnozik,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The XNNPack is disable in the actual version of tensorflow lite, however with the TensorFlow 2.3 release, XNNPACK backend is included with the pre-built TensorFlow Lite binaries for Linux and Android BSP.&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Regards&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 07 Jun 2021 13:15:56 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/xnnpack-in-tensorflow-lite-for-imx8-plus/m-p/1288317#M175124</guid>
      <dc:creator>Bio_TICFSL</dc:creator>
      <dc:date>2021-06-07T13:15:56Z</dc:date>
    </item>
    <item>
      <title>Re: xnnpack in tensorflow lite for imx8 plus</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/xnnpack-in-tensorflow-lite-for-imx8-plus/m-p/1288345#M175128</link>
      <description>&lt;P&gt;Hi ,&amp;nbsp;&lt;/P&gt;&lt;P&gt;thanks for reply .&lt;/P&gt;&lt;P&gt;1. Where can I find tensorflow lite prebuild library.&lt;/P&gt;&lt;P&gt;2.Does this prebuild library will also support IMX8 plus NPU delegate ?&lt;/P&gt;&lt;P&gt;3.We building all our libraries as part of image yocto recipe build , is there recipe with tensorflow branch with NNAPI and XNNPack for NPU/CPU ?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;thanks&lt;/P&gt;</description>
      <pubDate>Mon, 07 Jun 2021 13:44:14 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/xnnpack-in-tensorflow-lite-for-imx8-plus/m-p/1288345#M175128</guid>
      <dc:creator>dnozik</dc:creator>
      <dc:date>2021-06-07T13:44:14Z</dc:date>
    </item>
    <item>
      <title>Re: xnnpack in tensorflow lite for imx8 plus</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/xnnpack-in-tensorflow-lite-for-imx8-plus/m-p/1290764#M175352</link>
      <description>&lt;DIV id="bodyDisplay_0" class="lia-message-body lia-component-message-view-widget-body lia-component-body-signature-highlight-escalation lia-component-message-view-widget-body-signature-highlight-escalation"&gt;
&lt;DIV class="lia-message-body-content"&gt;
&lt;P&gt;Hello,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;For&amp;nbsp;&lt;SPAN&gt;TFLITE_WITHOUT_XNNPACK, it's disabled because not built with Makefile as below.&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;PRE class="lia-code-sample  language-markup"&gt;&lt;CODE&gt;commit b9b739285e46ca0bdc54641bf7351463cf8aa928
Author: Terry Heo &amp;lt;terryheo@google.com&amp;gt;
Date:   Thu Mar 19 05:03:41 2020 -0700

    Fix Makefile build

    Since XNNPACK isn't buildable with Makefile, it should be disabled for Makefile build.
&lt;/CODE&gt;&lt;/PRE&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;For 1# and 3#, BSP 5.10.9_1.0.0 is embedded with Tensorflow v2.4 and XNNPACK is enabled by default.&lt;/P&gt;
&lt;P&gt;As for 2#, from 5.10.9 user guide (IMXMLUG), XNNPACK goes through CPU but not NPU.&lt;/P&gt;
&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Bio_TICFSL_0-1623332657206.png" style="width: 400px;"&gt;&lt;img src="https://community.nxp.com/t5/image/serverpage/image-id/146829i9192A998198E3FCC/image-size/medium?v=v2&amp;amp;px=400" role="button" title="Bio_TICFSL_0-1623332657206.png" alt="Bio_TICFSL_0-1623332657206.png" /&gt;&lt;span class="lia-inline-image-caption" onclick="event.preventDefault();"&gt;Bio_TICFSL_0-1623332657206.png&lt;/span&gt;&lt;/span&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Regards&lt;/P&gt;
&lt;/DIV&gt;
&lt;/DIV&gt;</description>
      <pubDate>Thu, 10 Jun 2021 13:44:44 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/xnnpack-in-tensorflow-lite-for-imx8-plus/m-p/1290764#M175352</guid>
      <dc:creator>Bio_TICFSL</dc:creator>
      <dc:date>2021-06-10T13:44:44Z</dc:date>
    </item>
  </channel>
</rss>

