<?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 tensorflow lite benchmark_model and missing libneuralnetworks.so</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/tensorflow-lite-benchmark-model-and-missing-libneuralnetworks-so/m-p/1724106#M212673</link>
    <description>&lt;P&gt;I'm following the guide here:&lt;BR /&gt;&lt;A href="https://www.nxp.com/docs/en/user-guide/IMX_ANDROID_TENSORFLOWLITE_USERS_GUIDE.pdf" target="_blank"&gt;https://www.nxp.com/docs/en/user-guide/IMX_ANDROID_TENSORFLOWLITE_USERS_GUIDE.pdf&lt;/A&gt;&lt;/P&gt;&lt;P&gt;For compiling the benchmark_model and running the acceleration demo, I am not able to achieve acceleration as the document suggests.&lt;BR /&gt;We have the imx8mpevk board installed with Android 13-2.0.0&lt;BR /&gt;&amp;gt; uname -a&lt;BR /&gt;Linux localhost 6.1.25-android14-11-maybe-dirty #1 SMP PREEMPT Thu Jan 1 00:00:00 UTC 1970 aarch64 Toybox&lt;/P&gt;&lt;P&gt;&amp;gt; ./benchmark_model --graph=mobilenet_v1_1.0_224_quant.tflite --use_nnapi=1&lt;BR /&gt;STARTING!&lt;BR /&gt;Log parameter values verbosely: [0]&lt;BR /&gt;Graph: [mobilenet_v1_1.0_224_quant.tflite]&lt;BR /&gt;Use NNAPI: [1]&lt;BR /&gt;dlopen failed: library "libneuralnetworks.so" not found&lt;/P&gt;&lt;P&gt;nnapi error: unable to open library libneuralnetworks.so&lt;BR /&gt;Loaded model mobilenet_v1_1.0_224_quant.tflite&lt;BR /&gt;INFO: Initialized TensorFlow Lite runtime.&lt;BR /&gt;NNAPI acceleration is unsupported on this platform.&lt;/P&gt;&lt;P&gt;Is the documentation out of date for the proper way to compile benchmark_model to support acceleration? Or is there something we might be missing?&lt;BR /&gt;I tried with --use_gpu and the results were slower model execution than the CPU.&lt;/P&gt;</description>
    <pubDate>Fri, 15 Sep 2023 19:12:49 GMT</pubDate>
    <dc:creator>dennis3</dc:creator>
    <dc:date>2023-09-15T19:12:49Z</dc:date>
    <item>
      <title>tensorflow lite benchmark_model and missing libneuralnetworks.so</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/tensorflow-lite-benchmark-model-and-missing-libneuralnetworks-so/m-p/1724106#M212673</link>
      <description>&lt;P&gt;I'm following the guide here:&lt;BR /&gt;&lt;A href="https://www.nxp.com/docs/en/user-guide/IMX_ANDROID_TENSORFLOWLITE_USERS_GUIDE.pdf" target="_blank"&gt;https://www.nxp.com/docs/en/user-guide/IMX_ANDROID_TENSORFLOWLITE_USERS_GUIDE.pdf&lt;/A&gt;&lt;/P&gt;&lt;P&gt;For compiling the benchmark_model and running the acceleration demo, I am not able to achieve acceleration as the document suggests.&lt;BR /&gt;We have the imx8mpevk board installed with Android 13-2.0.0&lt;BR /&gt;&amp;gt; uname -a&lt;BR /&gt;Linux localhost 6.1.25-android14-11-maybe-dirty #1 SMP PREEMPT Thu Jan 1 00:00:00 UTC 1970 aarch64 Toybox&lt;/P&gt;&lt;P&gt;&amp;gt; ./benchmark_model --graph=mobilenet_v1_1.0_224_quant.tflite --use_nnapi=1&lt;BR /&gt;STARTING!&lt;BR /&gt;Log parameter values verbosely: [0]&lt;BR /&gt;Graph: [mobilenet_v1_1.0_224_quant.tflite]&lt;BR /&gt;Use NNAPI: [1]&lt;BR /&gt;dlopen failed: library "libneuralnetworks.so" not found&lt;/P&gt;&lt;P&gt;nnapi error: unable to open library libneuralnetworks.so&lt;BR /&gt;Loaded model mobilenet_v1_1.0_224_quant.tflite&lt;BR /&gt;INFO: Initialized TensorFlow Lite runtime.&lt;BR /&gt;NNAPI acceleration is unsupported on this platform.&lt;/P&gt;&lt;P&gt;Is the documentation out of date for the proper way to compile benchmark_model to support acceleration? Or is there something we might be missing?&lt;BR /&gt;I tried with --use_gpu and the results were slower model execution than the CPU.&lt;/P&gt;</description>
      <pubDate>Fri, 15 Sep 2023 19:12:49 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/tensorflow-lite-benchmark-model-and-missing-libneuralnetworks-so/m-p/1724106#M212673</guid>
      <dc:creator>dennis3</dc:creator>
      <dc:date>2023-09-15T19:12:49Z</dc:date>
    </item>
    <item>
      <title>Re: tensorflow lite benchmark_model and missing libneuralnetworks.so</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/tensorflow-lite-benchmark-model-and-missing-libneuralnetworks-so/m-p/1726336#M212876</link>
      <description>&lt;DIV class=""&gt;&lt;P&gt;&lt;SPAN class=""&gt;FYI I was able to work around this issue by updating the client library to Tensorflowlite version 2.10.1. I chose 2.10 because I noticed that was the version that the Linux distribution example was using.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&amp;nbsp;&lt;/SPAN&gt;&lt;SPAN class=""&gt;Version 2.10.1 w/ the benchmark_utility does not have the problem trying to find the &lt;/SPAN&gt;&lt;A title="" href="https://neuralnetworks.so" target="_blank" rel="noopener noreferrer"&gt;neuralnetworks.so&lt;/A&gt;&lt;SPAN class=""&gt; library.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&amp;nbsp;&lt;/SPAN&gt;&lt;SPAN class=""&gt;Questions remain:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;1) Is this just a case of outdated documentation?&lt;BR /&gt;2) If no, is there some technical reason to version 2.4 is still referenced in the tensorflowlite users guide?&lt;BR /&gt;3) If newer versions of TFlite are OK to use, is there a recommended version like 2.10, or would any newer version be appropriate?&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&amp;nbsp;&lt;/SPAN&gt;&lt;SPAN class=""&gt;Thanks.&lt;/SPAN&gt;&lt;/P&gt;&lt;/DIV&gt;</description>
      <pubDate>Wed, 20 Sep 2023 12:47:11 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/tensorflow-lite-benchmark-model-and-missing-libneuralnetworks-so/m-p/1726336#M212876</guid>
      <dc:creator>dennis3</dc:creator>
      <dc:date>2023-09-20T12:47:11Z</dc:date>
    </item>
    <item>
      <title>Re: tensorflow lite benchmark_model and missing libneuralnetworks.so</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/tensorflow-lite-benchmark-model-and-missing-libneuralnetworks-so/m-p/1727217#M212953</link>
      <description>&lt;P&gt;Hello,&lt;/P&gt;
&lt;P&gt;Thanks for update. We have built the image according to the guide and will test the benchmark model. So we will duplicate your findings. Anyway I will contact author of the documentation and check whether it is really not outdated.&lt;/P&gt;
&lt;P&gt;regards&lt;/P&gt;</description>
      <pubDate>Thu, 21 Sep 2023 14:45:17 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/tensorflow-lite-benchmark-model-and-missing-libneuralnetworks-so/m-p/1727217#M212953</guid>
      <dc:creator>Bio_TICFSL</dc:creator>
      <dc:date>2023-09-21T14:45:17Z</dc:date>
    </item>
  </channel>
</rss>

