<?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i.MX 8Mplus on android: failed to apply nnapi delegate</title>
    <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/i-MX-8Mplus-on-android-failed-to-apply-nnapi-delegate/m-p/1598437#M648</link>
    <description>&lt;P&gt;Hi, I am trying to run a face recognition model from i.MX 8Mplus with npu. My environment setting is shown below.&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;- Hardware: NXP i.XM 8Mplus&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;- Software: Android version 12 (Tried 10 and 11 but failed)&lt;BR /&gt;&lt;/SPAN&gt;Android SDK 33, NDK 21&lt;BR /&gt;&lt;SPAN&gt;- Model：insightface_quant (Downloaded&amp;nbsp;WebFace600K_pfc .onnx weight file from&amp;nbsp;&lt;A href="https://github.com/deepinsight/insightface/tree/master/model_zoo" target="_blank"&gt;https://github.com/deepinsight/insightface/tree/master/model_zoo&lt;/A&gt; and quantized into uint8 .tflite)&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;I used python 3.9 and tensorflow 2.11.0 for building tensorflow-lite via bazel. (Tried tf 2.4.0 first but failed as well). Both input and output type of quantized model is uint8.&lt;BR /&gt;I attached the error message, which is not really helpful for troubleshooting.&lt;BR /&gt;Both nnapi and xnnpack failed, while running on CPU without xnnpack succeeded.&lt;BR /&gt;Please help.&lt;/P&gt;</description>
    <pubDate>Mon, 13 Feb 2023 23:56:02 GMT</pubDate>
    <dc:creator>outburst</dc:creator>
    <dc:date>2023-02-13T23:56:02Z</dc:date>
    <item>
      <title>i.MX 8Mplus on android: failed to apply nnapi delegate</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/i-MX-8Mplus-on-android-failed-to-apply-nnapi-delegate/m-p/1598437#M648</link>
      <description>&lt;P&gt;Hi, I am trying to run a face recognition model from i.MX 8Mplus with npu. My environment setting is shown below.&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;- Hardware: NXP i.XM 8Mplus&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;- Software: Android version 12 (Tried 10 and 11 but failed)&lt;BR /&gt;&lt;/SPAN&gt;Android SDK 33, NDK 21&lt;BR /&gt;&lt;SPAN&gt;- Model：insightface_quant (Downloaded&amp;nbsp;WebFace600K_pfc .onnx weight file from&amp;nbsp;&lt;A href="https://github.com/deepinsight/insightface/tree/master/model_zoo" target="_blank"&gt;https://github.com/deepinsight/insightface/tree/master/model_zoo&lt;/A&gt; and quantized into uint8 .tflite)&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;I used python 3.9 and tensorflow 2.11.0 for building tensorflow-lite via bazel. (Tried tf 2.4.0 first but failed as well). Both input and output type of quantized model is uint8.&lt;BR /&gt;I attached the error message, which is not really helpful for troubleshooting.&lt;BR /&gt;Both nnapi and xnnpack failed, while running on CPU without xnnpack succeeded.&lt;BR /&gt;Please help.&lt;/P&gt;</description>
      <pubDate>Mon, 13 Feb 2023 23:56:02 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/i-MX-8Mplus-on-android-failed-to-apply-nnapi-delegate/m-p/1598437#M648</guid>
      <dc:creator>outburst</dc:creator>
      <dc:date>2023-02-13T23:56:02Z</dc:date>
    </item>
  </channel>
</rss>

