<?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 Re: NNAPI: using a delegate that only supports static-sized tensors with a graph that has dynamic te in i.MX Processors</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/NNAPI-using-a-delegate-that-only-supports-static-sized-tensors/m-p/1335508#M179624</link>
    <description>&lt;P&gt;Hello jasonliu1,&lt;/P&gt;
&lt;P&gt;One possible reason here is that when you use eIQ software to convert the custom model, you choose MLIR as tflite converter. I will recommend to use TOCO instead and see whether this problem is avoided. Thank you.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Mon, 06 Sep 2021 12:51:30 GMT</pubDate>
    <dc:creator>Bio_TICFSL</dc:creator>
    <dc:date>2021-09-06T12:51:30Z</dc:date>
    <item>
      <title>NNAPI: using a delegate that only supports static-sized tensors with a graph that has dynamic tensor</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/NNAPI-using-a-delegate-that-only-supports-static-sized-tensors/m-p/1333497#M179460</link>
      <description>&lt;P&gt;Hi,&amp;nbsp;&lt;/P&gt;&lt;P&gt;I started training a fpn-ssd-mobilenetv2 model(which is one of the base models provided by the eIQ software) using custom dataset on the software recently. However, when I converted it into a tflite model and implemented it on a board with NNAPI delegate, it tells me that I'm "attempting to use a delegate that only supports static-sized tensors with a graph that has dynamic-sized tensors" and it failed to apply NNAPI delegate.&amp;nbsp;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I was just wondering what is the cause of this problem and what should I do to avoid it?&lt;/P&gt;&lt;P&gt;Thanks very much!&lt;/P&gt;</description>
      <pubDate>Wed, 01 Sep 2021 19:46:35 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/NNAPI-using-a-delegate-that-only-supports-static-sized-tensors/m-p/1333497#M179460</guid>
      <dc:creator>jasonliu1</dc:creator>
      <dc:date>2021-09-01T19:46:35Z</dc:date>
    </item>
    <item>
      <title>Re: NNAPI: using a delegate that only supports static-sized tensors with a graph that has dynamic te</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/NNAPI-using-a-delegate-that-only-supports-static-sized-tensors/m-p/1335508#M179624</link>
      <description>&lt;P&gt;Hello jasonliu1,&lt;/P&gt;
&lt;P&gt;One possible reason here is that when you use eIQ software to convert the custom model, you choose MLIR as tflite converter. I will recommend to use TOCO instead and see whether this problem is avoided. Thank you.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 06 Sep 2021 12:51:30 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/NNAPI-using-a-delegate-that-only-supports-static-sized-tensors/m-p/1335508#M179624</guid>
      <dc:creator>Bio_TICFSL</dc:creator>
      <dc:date>2021-09-06T12:51:30Z</dc:date>
    </item>
  </channel>
</rss>

