<?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のトピックRe: Running TensorFlow on imx6sxsabresd</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/Running-TensorFlow-on-imx6sxsabresd/m-p/1232035#M169609</link>
    <description>&lt;P&gt;However, I heard that eiq is not possible in imx6 solo, but tensorflow is possible in the latest version of bsp (imx-image-full). Doesn't this also work? So I built with bitbake imx-image-full.&lt;/P&gt;</description>
    <pubDate>Wed, 17 Feb 2021 11:27:21 GMT</pubDate>
    <dc:creator>deflight</dc:creator>
    <dc:date>2021-02-17T11:27:21Z</dc:date>
    <item>
      <title>Running TensorFlow on imx6sxsabresd</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Running-TensorFlow-on-imx6sxsabresd/m-p/1231893#M169597</link>
      <description>&lt;P&gt;Hi i have imx6sxsabresd board.&lt;/P&gt;&lt;P&gt;My goal was to build with the tensorflow meta-ml package.&lt;/P&gt;&lt;P&gt;I built it with the following command according to the manual&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;EULA=1 DISTRO=fsl-imx-xwayland MACHINE=imx6sxsabresd source imx-setup-release.sh -b build-xwayland&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;mkdir ~/bin&lt;BR /&gt;curl &lt;A href="https://storage.googleapis.com/git-repo-downloads/repo" target="_blank"&gt;https://storage.googleapis.com/git-repo-downloads/repo&lt;/A&gt; &amp;gt; ~/bin/repo&lt;BR /&gt;chmod a+x ~/bin/repo&lt;BR /&gt;PATH=${PATH}:~/bin&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;mkdir imx-yocto-bsp&lt;BR /&gt;cd imx-yocto-bsp&lt;/P&gt;&lt;P&gt;repo init -u &lt;A href="https://source.codeaurora.org/external/imx/imx-manifest" target="_blank"&gt;https://source.codeaurora.org/external/imx/imx-manifest&lt;/A&gt; -b imx-linux-zeus -m imx-5.4.70-2.3.0.xml&lt;/P&gt;&lt;P&gt;repo sync&lt;/P&gt;&lt;P&gt;However, the meta-ml package was not included and built.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;I looked up the relevant bb files.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;armnn_git.bb&lt;/P&gt;&lt;P&gt;# We support i.MX8 only (for now)&lt;BR /&gt;COMPATIBLE_MACHINE = "(mx8)"&lt;/P&gt;&lt;P&gt;tensorflow-lite.bb&lt;/P&gt;&lt;P&gt;RDEPENDS_MX8 = ""&lt;BR /&gt;RDEPENDS_MX8_mx8 = "libnn-imx nn-imx"&lt;BR /&gt;RDEPENDS_MX8_mx8mm = ""&lt;BR /&gt;RDEPENDS_${PN} = " \&lt;BR /&gt;flatbuffers \&lt;BR /&gt;python3 \&lt;BR /&gt;python3-numpy \&lt;BR /&gt;${RDEPENDS_MX8} \&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;It was written as.&lt;/P&gt;&lt;P&gt;In the old technical consultation, I heard that TensorFlow is powered by a CPU on my board.&lt;/P&gt;&lt;P&gt;Is this not possible?&lt;/P&gt;</description>
      <pubDate>Wed, 17 Feb 2021 07:23:45 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Running-TensorFlow-on-imx6sxsabresd/m-p/1231893#M169597</guid>
      <dc:creator>deflight</dc:creator>
      <dc:date>2021-02-17T07:23:45Z</dc:date>
    </item>
    <item>
      <title>Re: Running TensorFlow on imx6sxsabresd</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Running-TensorFlow-on-imx6sxsabresd/m-p/1231979#M169604</link>
      <description>&lt;P&gt;Yes, only i.mx8 serials processor support eIQ and machine learning. See below, please!&lt;/P&gt;
&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="weidong_sun_0-1613555328312.png" style="width: 400px;"&gt;&lt;img src="https://community.nxp.com/t5/image/serverpage/image-id/137334i1393F0C876DEE289/image-size/medium?v=v2&amp;amp;px=400" role="button" title="weidong_sun_0-1613555328312.png" alt="weidong_sun_0-1613555328312.png" /&gt;&lt;/span&gt;&lt;/P&gt;
&lt;P&gt;&lt;A href="https://www.nxp.com/design/software/development-software/eiq-ml-development-environment:EIQ" target="_blank"&gt;https://www.nxp.com/design/software/development-software/eiq-ml-development-environment:EIQ&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Have a&amp;nbsp; nice day!&lt;/P&gt;
&lt;P&gt;B.R,&lt;/P&gt;
&lt;P&gt;weidong&lt;/P&gt;</description>
      <pubDate>Wed, 17 Feb 2021 09:49:24 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Running-TensorFlow-on-imx6sxsabresd/m-p/1231979#M169604</guid>
      <dc:creator>weidong_sun</dc:creator>
      <dc:date>2021-02-17T09:49:24Z</dc:date>
    </item>
    <item>
      <title>Re: Running TensorFlow on imx6sxsabresd</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Running-TensorFlow-on-imx6sxsabresd/m-p/1232035#M169609</link>
      <description>&lt;P&gt;However, I heard that eiq is not possible in imx6 solo, but tensorflow is possible in the latest version of bsp (imx-image-full). Doesn't this also work? So I built with bitbake imx-image-full.&lt;/P&gt;</description>
      <pubDate>Wed, 17 Feb 2021 11:27:21 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Running-TensorFlow-on-imx6sxsabresd/m-p/1232035#M169609</guid>
      <dc:creator>deflight</dc:creator>
      <dc:date>2021-02-17T11:27:21Z</dc:date>
    </item>
    <item>
      <title>Re: Running TensorFlow on imx6sxsabresd</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Running-TensorFlow-on-imx6sxsabresd/m-p/1233411#M169721</link>
      <description>&lt;P&gt;&lt;SPAN class="VIiyi"&gt;&lt;SPAN class="JLqJ4b ChMk0b" data-language-for-alternatives="en" data-language-to-translate-into="zh-CN" data-phrase-index="0"&gt;&lt;SPAN&gt;I added and tested tensorflow-lite in Yocto for i.mx6sx. The meta-ml packages were needed during the compilation process, but the compilation failed.&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Fri, 19 Feb 2021 07:24:17 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Running-TensorFlow-on-imx6sxsabresd/m-p/1233411#M169721</guid>
      <dc:creator>weidong_sun</dc:creator>
      <dc:date>2021-02-19T07:24:17Z</dc:date>
    </item>
  </channel>
</rss>

