<?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>eIQ Machine Learning SoftwareのトピックWhy example with target set to OpenCl is not running for dnn if Opencl is enabled,</title>
    <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966985#M25</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Target is imx8qxp&lt;/P&gt;&lt;P&gt;example: /usr/share/OpenCV/samples/bin/example_dnn_object_detection&lt;/P&gt;&lt;P&gt;Linux: 4.14.78+&lt;/P&gt;&lt;P&gt;Checked after Enabling opencl.&lt;/P&gt;&lt;P&gt;Command: /usr/share/OpenCV/samples/bin/example_dnn_object_detection -scale=0.00392 -rgb -device=7 -target=1 -zoo=models.yml yolo [provided all dependency files, running fine with -target=0 (CPU)]. but not running if -target is set to 1/2.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Please let us know the behaviour or limitation of software/hardware?&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Thu, 24 Oct 2019 17:09:25 GMT</pubDate>
    <dc:creator>sandeep_rai</dc:creator>
    <dc:date>2019-10-24T17:09:25Z</dc:date>
    <item>
      <title>Why example with target set to OpenCl is not running for dnn if Opencl is enabled,</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966985#M25</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Target is imx8qxp&lt;/P&gt;&lt;P&gt;example: /usr/share/OpenCV/samples/bin/example_dnn_object_detection&lt;/P&gt;&lt;P&gt;Linux: 4.14.78+&lt;/P&gt;&lt;P&gt;Checked after Enabling opencl.&lt;/P&gt;&lt;P&gt;Command: /usr/share/OpenCV/samples/bin/example_dnn_object_detection -scale=0.00392 -rgb -device=7 -target=1 -zoo=models.yml yolo [provided all dependency files, running fine with -target=0 (CPU)]. but not running if -target is set to 1/2.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Please let us know the behaviour or limitation of software/hardware?&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 24 Oct 2019 17:09:25 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966985#M25</guid>
      <dc:creator>sandeep_rai</dc:creator>
      <dc:date>2019-10-24T17:09:25Z</dc:date>
    </item>
    <item>
      <title>Re: Why example with target set to OpenCl is not running for dnn if Opencl is enabled,</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966986#M26</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;OpenCL is currently not supported on eIQ L4.14.&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 24 Oct 2019 17:27:49 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966986#M26</guid>
      <dc:creator>vanessa_maegima</dc:creator>
      <dc:date>2019-10-24T17:27:49Z</dc:date>
    </item>
    <item>
      <title>Re: Why example with target set to OpenCl is not running for dnn if Opencl is enabled,</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966987#M27</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Sandeep,&lt;BR /&gt; &lt;BR /&gt;As Vanessa mentioned, OpenCL is currently not supported in the L4.14.98_2.0.0 and L4.14.78_1.0.0 Yocto configurations. This is a software limitation documented in eIQ app note UM11226 that we expect will be resolved in a future release.&lt;BR /&gt; &lt;BR /&gt;Regards,&lt;BR /&gt;Ragan&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 24 Oct 2019 17:31:54 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966987#M27</guid>
      <dc:creator>Ragan_Dunham</dc:creator>
      <dc:date>2019-10-24T17:31:54Z</dc:date>
    </item>
    <item>
      <title>Re: Why example with target set to OpenCl is not running for dnn if Opencl is enabled,</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966988#M28</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hi Ragan,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Could you please let us know in which existing version for yocto, opencl is working?&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;We have some demo for machine learning which is working fine with cpu (but slow response and lower frame rate), but not running with opencl/opencl_fp16.&lt;/P&gt;&lt;P&gt;I have enabled the opencl packages and watched the behaviour says, process is taking much gpu memory continously and sometimes process gets terminated as memory gets full.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Is it a way to reduce the time for machine learning while object detection with opencl (gpu utilisation), but there is only one gpu core and 4 shaders, does it perform well?&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Let me know about whether opencl_fp16 support? Because it may use sometimes lower memory but faster response for frame rate?&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;...&lt;/P&gt;&lt;P&gt;Thanks&lt;/P&gt;&lt;P&gt;Sandeep K Rai&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Get Outlook for Android&amp;lt;https://aka.ms/ghei36&amp;gt;&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 24 Oct 2019 19:20:50 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966988#M28</guid>
      <dc:creator>sandeep_rai</dc:creator>
      <dc:date>2019-10-24T19:20:50Z</dc:date>
    </item>
    <item>
      <title>Re: Why example with target set to OpenCl is not running for dnn if Opencl is enabled,</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966989#M29</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Sandeep,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;It is not yet specified when OpenCL support for ML will be available. We continue to work on this enablement but at this time I cannot provide any further guidance on the timeline or anticipated kernel version.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Best Regards,&lt;/P&gt;&lt;P&gt;Ragan&amp;nbsp;&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 24 Oct 2019 19:33:03 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Why-example-with-target-set-to-OpenCl-is-not-running-for-dnn-if/m-p/966989#M29</guid>
      <dc:creator>Ragan_Dunham</dc:creator>
      <dc:date>2019-10-24T19:33:03Z</dc:date>
    </item>
  </channel>
</rss>

