<?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: Deepview SDK to convert pyTorch model</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/Deepview-SDK-to-convert-pyTorch-model/m-p/1294712#M175713</link>
    <description>&lt;P&gt;Good!&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Fri, 18 Jun 2021 13:04:23 GMT</pubDate>
    <dc:creator>Bio_TICFSL</dc:creator>
    <dc:date>2021-06-18T13:04:23Z</dc:date>
    <item>
      <title>Deepview SDK to convert pyTorch model</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Deepview-SDK-to-convert-pyTorch-model/m-p/1294537#M175697</link>
      <description>&lt;P&gt;&lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/30869"&gt;@xiaodong_zhang&lt;/a&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;Right now we have a algorithm base on pyTorch , we run this model in the I.MX8M mini and I.MX8M plus , they are also slow. When can we get the Deepview SDK ?&amp;nbsp;&lt;/P&gt;&lt;P&gt;As I know , with using the Deepview SDK , we can convert the poTorch model to the converted model which can be accelerate computation by I.MX8M puls NPU .&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 18 Jun 2021 08:06:36 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Deepview-SDK-to-convert-pyTorch-model/m-p/1294537#M175697</guid>
      <dc:creator>Arrow_AE_KingLiu</dc:creator>
      <dc:date>2021-06-18T08:06:36Z</dc:date>
    </item>
    <item>
      <title>Re: Deepview SDK to convert pyTorch model</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Deepview-SDK-to-convert-pyTorch-model/m-p/1294601#M175705</link>
      <description>&lt;P&gt;&lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/96361"&gt;@Arrow_AE_KingLiu&lt;/a&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;As I know, Deepview SDK will release at July this year.&lt;/P&gt;</description>
      <pubDate>Fri, 18 Jun 2021 09:30:35 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Deepview-SDK-to-convert-pyTorch-model/m-p/1294601#M175705</guid>
      <dc:creator>xiaodong_zhang</dc:creator>
      <dc:date>2021-06-18T09:30:35Z</dc:date>
    </item>
    <item>
      <title>Re: Deepview SDK to convert pyTorch model</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Deepview-SDK-to-convert-pyTorch-model/m-p/1294602#M175706</link>
      <description>&lt;P&gt;&lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/30869"&gt;@xiaodong_zhang&lt;/a&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;If we can share the algorithm source code to you , can you help to convert it for test firstly ?&lt;/P&gt;</description>
      <pubDate>Fri, 18 Jun 2021 09:33:28 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Deepview-SDK-to-convert-pyTorch-model/m-p/1294602#M175706</guid>
      <dc:creator>Arrow_AE_KingLiu</dc:creator>
      <dc:date>2021-06-18T09:33:28Z</dc:date>
    </item>
    <item>
      <title>Re: Deepview SDK to convert pyTorch model</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Deepview-SDK-to-convert-pyTorch-model/m-p/1294712#M175713</link>
      <description>&lt;P&gt;Good!&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 18 Jun 2021 13:04:23 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Deepview-SDK-to-convert-pyTorch-model/m-p/1294712#M175713</guid>
      <dc:creator>Bio_TICFSL</dc:creator>
      <dc:date>2021-06-18T13:04:23Z</dc:date>
    </item>
  </channel>
</rss>

