<?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 8M Quad support to deep learning frameworks? in i.MX Processors</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/8M-Quad-support-to-deep-learning-frameworks/m-p/870556#M132365</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hi,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I have been thinking about this question for a while: is the 8M quad that industrial version capable to run frameworks like Tensorflow or/and Caffe and processing the moving object recognition? Of course the image processing includes in that question.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;The framework will be driven under operating system, Linux.&lt;/P&gt;&lt;P&gt;I think its capable to that, but there would be some problems on timing the process.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I have planned to use 5 MP camera based on OV5640 chip and some small HD-scale colored TFT-screen. Both maybe connected by the MIPI bus.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;The timing between input and output (camera -&amp;gt; image processing -&amp;gt; recognition -&amp;gt; result on the screen with the picture).&lt;/P&gt;&lt;P&gt;I expect like realtime results on output (min 30 fps), so the time to output per picture can be something like 30 milliseconds at least.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Is the i.MX 8M Quad or even QuadLite capable to run process with these limits?&lt;/P&gt;&lt;P&gt;Or is it better to just wait the i.MX 8 launch?&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Thanks in advance&lt;/P&gt;&lt;P&gt;Br. Roger&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Fri, 11 Jan 2019 12:09:43 GMT</pubDate>
    <dc:creator>roger_kupari</dc:creator>
    <dc:date>2019-01-11T12:09:43Z</dc:date>
    <item>
      <title>8M Quad support to deep learning frameworks?</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/8M-Quad-support-to-deep-learning-frameworks/m-p/870556#M132365</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hi,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I have been thinking about this question for a while: is the 8M quad that industrial version capable to run frameworks like Tensorflow or/and Caffe and processing the moving object recognition? Of course the image processing includes in that question.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;The framework will be driven under operating system, Linux.&lt;/P&gt;&lt;P&gt;I think its capable to that, but there would be some problems on timing the process.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I have planned to use 5 MP camera based on OV5640 chip and some small HD-scale colored TFT-screen. Both maybe connected by the MIPI bus.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;The timing between input and output (camera -&amp;gt; image processing -&amp;gt; recognition -&amp;gt; result on the screen with the picture).&lt;/P&gt;&lt;P&gt;I expect like realtime results on output (min 30 fps), so the time to output per picture can be something like 30 milliseconds at least.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Is the i.MX 8M Quad or even QuadLite capable to run process with these limits?&lt;/P&gt;&lt;P&gt;Or is it better to just wait the i.MX 8 launch?&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Thanks in advance&lt;/P&gt;&lt;P&gt;Br. Roger&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Fri, 11 Jan 2019 12:09:43 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/8M-Quad-support-to-deep-learning-frameworks/m-p/870556#M132365</guid>
      <dc:creator>roger_kupari</dc:creator>
      <dc:date>2019-01-11T12:09:43Z</dc:date>
    </item>
    <item>
      <title>Re: 8M Quad support to deep learning frameworks?</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/8M-Quad-support-to-deep-learning-frameworks/m-p/870557#M132366</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hi Roger,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;The i.MX8M is capable of running Tensorflow or/and Caffe and support deep learning frameworks.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Regards&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Mon, 14 Jan 2019 14:44:02 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/8M-Quad-support-to-deep-learning-frameworks/m-p/870557#M132366</guid>
      <dc:creator>Bio_TICFSL</dc:creator>
      <dc:date>2019-01-14T14:44:02Z</dc:date>
    </item>
    <item>
      <title>Re: 8M Quad support to deep learning frameworks?</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/8M-Quad-support-to-deep-learning-frameworks/m-p/870558#M132367</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Tensorflow or Tensorflowlite is better for moving object detection in i.MX8M&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Mon, 25 Feb 2019 05:36:27 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/8M-Quad-support-to-deep-learning-frameworks/m-p/870558#M132367</guid>
      <dc:creator>PramodKumar</dc:creator>
      <dc:date>2019-02-25T05:36:27Z</dc:date>
    </item>
  </channel>
</rss>

