<?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 IMX 8M Plus, Runtime Error on making tflite-runtime interpreter with delegate (libvx_delegate.so)</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/IMX-8M-Plus-Runtime-Error-on-making-tflite-runtime-interpreter/m-p/1592979#M201007</link>
    <description>&lt;P&gt;&lt;STRONG&gt;IMX 8M Plus, Runtime Error on making tflite-runtime interpreter with delegate (libvx_delegate.so)&lt;/STRONG&gt;&lt;/P&gt;&lt;P&gt;Platform = NXP-imx8mp-lpddr4-evk&lt;/P&gt;&lt;P&gt;Linux Kernel Release = 5.15.32-lts-next+gfa6c3168595c&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;made an efficientnet model using:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;LI-CODE lang="python"&gt;from tensorflow.keras.applications import EfficientNetB0
model = EfficientNetB0(weights='imagenet')&lt;/LI-CODE&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;- Then converted the same to int8-tflite format to be able to run it on the NPU, while trying to run the same model on npu I got this strange runtime error with no details :&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;LI-CODE lang="markup"&gt;Traceback (most recent call last):
  File "/home/root/xyz/tflite_detection_live.py", line 143, in &amp;lt;module&amp;gt;
    main()
  File "/home/root/xyz/tflite_detection_live.py", line 78, in main
    c_interpreter = make_interpreter(args.classifier_model, args.use_npu)
  File "/home/root/xyz/tflite_detection_live.py", line 22, in make_interpreter
    return Interpreter(
  File "/usr/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 496, in __init__
    self._interpreter.ModifyGraphWithDelegate(
RuntimeError&lt;/LI-CODE&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;Note : This same model runs fine on the CPU.&lt;/P&gt;&lt;P&gt;- To check if there was something wrong in the conversion process, I tried to do the same with&amp;nbsp;&lt;SPAN&gt;keras.applications.mobilenet_v2 and that model ran fine on NPU as well as the CPU.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;- Looks like there can be some issues with the "libvx_delegate.so" being used.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;- Any pointers as to how to run this efficientnet model on the NPU?&lt;/SPAN&gt;&lt;/P&gt;</description>
    <pubDate>Fri, 03 Feb 2023 08:55:42 GMT</pubDate>
    <dc:creator>kandarp_rastey</dc:creator>
    <dc:date>2023-02-03T08:55:42Z</dc:date>
    <item>
      <title>IMX 8M Plus, Runtime Error on making tflite-runtime interpreter with delegate (libvx_delegate.so)</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/IMX-8M-Plus-Runtime-Error-on-making-tflite-runtime-interpreter/m-p/1592979#M201007</link>
      <description>&lt;P&gt;&lt;STRONG&gt;IMX 8M Plus, Runtime Error on making tflite-runtime interpreter with delegate (libvx_delegate.so)&lt;/STRONG&gt;&lt;/P&gt;&lt;P&gt;Platform = NXP-imx8mp-lpddr4-evk&lt;/P&gt;&lt;P&gt;Linux Kernel Release = 5.15.32-lts-next+gfa6c3168595c&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;made an efficientnet model using:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;LI-CODE lang="python"&gt;from tensorflow.keras.applications import EfficientNetB0
model = EfficientNetB0(weights='imagenet')&lt;/LI-CODE&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;- Then converted the same to int8-tflite format to be able to run it on the NPU, while trying to run the same model on npu I got this strange runtime error with no details :&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;LI-CODE lang="markup"&gt;Traceback (most recent call last):
  File "/home/root/xyz/tflite_detection_live.py", line 143, in &amp;lt;module&amp;gt;
    main()
  File "/home/root/xyz/tflite_detection_live.py", line 78, in main
    c_interpreter = make_interpreter(args.classifier_model, args.use_npu)
  File "/home/root/xyz/tflite_detection_live.py", line 22, in make_interpreter
    return Interpreter(
  File "/usr/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 496, in __init__
    self._interpreter.ModifyGraphWithDelegate(
RuntimeError&lt;/LI-CODE&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;Note : This same model runs fine on the CPU.&lt;/P&gt;&lt;P&gt;- To check if there was something wrong in the conversion process, I tried to do the same with&amp;nbsp;&lt;SPAN&gt;keras.applications.mobilenet_v2 and that model ran fine on NPU as well as the CPU.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;- Looks like there can be some issues with the "libvx_delegate.so" being used.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;- Any pointers as to how to run this efficientnet model on the NPU?&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Fri, 03 Feb 2023 08:55:42 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/IMX-8M-Plus-Runtime-Error-on-making-tflite-runtime-interpreter/m-p/1592979#M201007</guid>
      <dc:creator>kandarp_rastey</dc:creator>
      <dc:date>2023-02-03T08:55:42Z</dc:date>
    </item>
    <item>
      <title>Re: IMX 8M Plus, Runtime Error on making tflite-runtime interpreter with delegate (libvx_delegate.so</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/IMX-8M-Plus-Runtime-Error-on-making-tflite-runtime-interpreter/m-p/1593216#M201025</link>
      <description>&lt;P&gt;Hello,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Please try the latest bsp 5.15.71, since your kernel version is not supported, you may try the latest one.&lt;/P&gt;
&lt;P&gt;Regards&lt;/P&gt;</description>
      <pubDate>Fri, 03 Feb 2023 14:55:01 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/IMX-8M-Plus-Runtime-Error-on-making-tflite-runtime-interpreter/m-p/1593216#M201025</guid>
      <dc:creator>Bio_TICFSL</dc:creator>
      <dc:date>2023-02-03T14:55:01Z</dc:date>
    </item>
    <item>
      <title>Re: IMX 8M Plus, Runtime Error on making tflite-runtime interpreter with delegate (libvx_delegate.so</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/IMX-8M-Plus-Runtime-Error-on-making-tflite-runtime-interpreter/m-p/1593849#M201077</link>
      <description>&lt;P&gt;- yes, tried to run the same on a variscite imx8mplus evk with kernel =&amp;nbsp; 5.15.60-imx8mp+g15e390fe9060.&lt;/P&gt;&lt;P&gt;- But, got the same runtime error.&lt;/P&gt;</description>
      <pubDate>Mon, 06 Feb 2023 09:34:38 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/IMX-8M-Plus-Runtime-Error-on-making-tflite-runtime-interpreter/m-p/1593849#M201077</guid>
      <dc:creator>kandarp_rastey</dc:creator>
      <dc:date>2023-02-06T09:34:38Z</dc:date>
    </item>
  </channel>
</rss>

