<?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 DeepView Python API - eIQ Toolkit</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/DeepView-Python-API-eIQ-Toolkit/m-p/1348497#M180833</link>
    <description>&lt;P&gt;Hey,&lt;/P&gt;&lt;P&gt;I am trying to use the deepview ModelClient API to run a CNN at inference. Because right now I am at first trying to run this on the local host, the later chip technology is trivial to mention. I ran the deeplab_v3 segmentation example and it worked. However, loading my CNN fails with the error-msg: " 'error': 'model load error' ". The code is actually (in minimal form) just calling&lt;/P&gt;&lt;P&gt;from deepview.rt.modelclient import ModelClient&lt;BR /&gt;modelclient = ModelClient("&lt;A href="http://127.0.0.1:10818/v1" target="_blank"&gt;http://127.0.0.1:10818/v1&lt;/A&gt;", path_to_rtm)&lt;/P&gt;&lt;P&gt;As mentioned, is path_to_rtm the deelab_v3 model from the example folder the code runs through without errors. If path_to_rtm is my CNN (Converted using the eIQ interface from .h5 as well as from .tflite to .rtm) leading to the mentioned error.&lt;/P&gt;&lt;P&gt;Do you have any idea why it isnt working, although the conversion(using th eIQ Toolkit) of my CNN to .rtm ran without errors ?&lt;/P&gt;&lt;P&gt;Would be very happy about any hints.&lt;/P&gt;</description>
    <pubDate>Wed, 29 Sep 2021 15:40:03 GMT</pubDate>
    <dc:creator>horst127</dc:creator>
    <dc:date>2021-09-29T15:40:03Z</dc:date>
    <item>
      <title>DeepView Python API - eIQ Toolkit</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/DeepView-Python-API-eIQ-Toolkit/m-p/1348497#M180833</link>
      <description>&lt;P&gt;Hey,&lt;/P&gt;&lt;P&gt;I am trying to use the deepview ModelClient API to run a CNN at inference. Because right now I am at first trying to run this on the local host, the later chip technology is trivial to mention. I ran the deeplab_v3 segmentation example and it worked. However, loading my CNN fails with the error-msg: " 'error': 'model load error' ". The code is actually (in minimal form) just calling&lt;/P&gt;&lt;P&gt;from deepview.rt.modelclient import ModelClient&lt;BR /&gt;modelclient = ModelClient("&lt;A href="http://127.0.0.1:10818/v1" target="_blank"&gt;http://127.0.0.1:10818/v1&lt;/A&gt;", path_to_rtm)&lt;/P&gt;&lt;P&gt;As mentioned, is path_to_rtm the deelab_v3 model from the example folder the code runs through without errors. If path_to_rtm is my CNN (Converted using the eIQ interface from .h5 as well as from .tflite to .rtm) leading to the mentioned error.&lt;/P&gt;&lt;P&gt;Do you have any idea why it isnt working, although the conversion(using th eIQ Toolkit) of my CNN to .rtm ran without errors ?&lt;/P&gt;&lt;P&gt;Would be very happy about any hints.&lt;/P&gt;</description>
      <pubDate>Wed, 29 Sep 2021 15:40:03 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/DeepView-Python-API-eIQ-Toolkit/m-p/1348497#M180833</guid>
      <dc:creator>horst127</dc:creator>
      <dc:date>2021-09-29T15:40:03Z</dc:date>
    </item>
    <item>
      <title>Re: DeepView Python API - eIQ Toolkit</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/DeepView-Python-API-eIQ-Toolkit/m-p/1351418#M181150</link>
      <description>&lt;P&gt;Hello horst,&lt;/P&gt;
&lt;P&gt;Can you share the model you used?&lt;/P&gt;
&lt;P&gt;I assume the error you see appeared on the host PC. Any message shown on the board?&lt;/P&gt;
&lt;P&gt;Please share the log from %appdata%Roaming\eIQ Portal\logs\&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Regards&lt;/P&gt;</description>
      <pubDate>Wed, 06 Oct 2021 18:13:34 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/DeepView-Python-API-eIQ-Toolkit/m-p/1351418#M181150</guid>
      <dc:creator>Bio_TICFSL</dc:creator>
      <dc:date>2021-10-06T18:13:34Z</dc:date>
    </item>
  </channel>
</rss>

