<?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: Question about how to integrate ML model into FRDM-MCXN947 by tflm_ciar10 project in MCX Microcontrollers</title>
    <link>https://community.nxp.com/t5/MCX-Microcontrollers/Question-about-how-to-integrate-ML-model-into-FRDM-MCXN947-by/m-p/1895859#M515</link>
    <description>&lt;P&gt;Hello&amp;nbsp;&lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/230805"&gt;@BillWen&lt;/a&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;There is simple guide demonstrating the steps. Also includes video. Please refer to it:&lt;/P&gt;
&lt;P&gt;&lt;A href="https://www.nxpic.org.cn/module/forum/forum.php?mod=viewthread&amp;amp;tid=803297&amp;amp;page=1&amp;amp;extra=#pid3004813" target="_blank"&gt;https://www.nxpic.org.cn/module/forum/forum.php?mod=viewthread&amp;amp;tid=803297&amp;amp;page=1&amp;amp;extra=#pid3004813&lt;/A&gt;&amp;nbsp;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;BR&lt;/P&gt;
&lt;P&gt;Alice&lt;/P&gt;</description>
    <pubDate>Fri, 28 Jun 2024 10:17:27 GMT</pubDate>
    <dc:creator>Alice_Yang</dc:creator>
    <dc:date>2024-06-28T10:17:27Z</dc:date>
    <item>
      <title>Question about how to integrate ML model into FRDM-MCXN947 by tflm_ciar10 project</title>
      <link>https://community.nxp.com/t5/MCX-Microcontrollers/Question-about-how-to-integrate-ML-model-into-FRDM-MCXN947-by/m-p/1892478#M497</link>
      <description>&lt;P&gt;Hi Everyone:&lt;/P&gt;&lt;P&gt;My environment :&amp;nbsp;&lt;/P&gt;&lt;P&gt;1.&amp;nbsp;MCUXpressoIDE_11.9.1&lt;/P&gt;&lt;P&gt;2. eIQ Toolkit v1.11.4&lt;/P&gt;&lt;P&gt;3.&amp;nbsp;SDK_2_14_0_FRDM-MCXN947&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I try to put my ML model into&amp;nbsp;FRDM-MCXN947 by tflm_ciar10 project, the following is my steps:&lt;/P&gt;&lt;P&gt;1. Use eIQ toolkit to transfer LSTM model from .h5 file to Tensorflow Lite, and transfer again from&amp;nbsp;Tensorflow Lite to&amp;nbsp;Tensorflow Lite for Neutron&lt;/P&gt;&lt;P&gt;2. Follow the document "How to Integrate Customer ML Model to NPU on MCX N94x" -&amp;gt; AN14241 to put my model into project&lt;/P&gt;&lt;P&gt;3. Setup a test data, and put into project. If my test data is .mat or .blf file, can I put inside or I should transfer it to .h file first?&lt;/P&gt;&lt;P&gt;4. build successful&lt;/P&gt;&lt;P&gt;5. power on device and error&lt;/P&gt;&lt;P&gt;&lt;STRONG&gt;CIFAR-10 example using a TensorFlow Lite Micro model.&lt;/STRONG&gt;&lt;BR /&gt;&lt;STRONG&gt;Detection threshold: 60%&lt;/STRONG&gt;&lt;BR /&gt;&lt;STRONG&gt;Model: cifarnet_quant_int8_npu&lt;/STRONG&gt;&lt;BR /&gt;&lt;STRONG&gt;Didn't find op for builtin opcode 'UNIDIRECTIONAL_SEQUENCE_LSTM'&lt;/STRONG&gt;&lt;BR /&gt;&lt;STRONG&gt;Failed to get registration from op code UNIDIRECTIONAL_SEQUENCE_LSTM&lt;/STRONG&gt;&lt;/P&gt;&lt;P&gt;&lt;STRONG&gt;AllocateTensors() failedFailed initializing model&lt;/STRONG&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Do anyone have experience on this situation?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;BTW, where can I get the demo model and test data according to&amp;nbsp;AN14241 document? I can't find the path or reference about it, thanks.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks a lot&lt;/P&gt;&lt;P&gt;BR, Bill Wen&lt;/P&gt;</description>
      <pubDate>Mon, 24 Jun 2024 01:33:10 GMT</pubDate>
      <guid>https://community.nxp.com/t5/MCX-Microcontrollers/Question-about-how-to-integrate-ML-model-into-FRDM-MCXN947-by/m-p/1892478#M497</guid>
      <dc:creator>BillWen</dc:creator>
      <dc:date>2024-06-24T01:33:10Z</dc:date>
    </item>
    <item>
      <title>Re: Question about how to integrate ML model into FRDM-MCXN947 by tflm_ciar10 project</title>
      <link>https://community.nxp.com/t5/MCX-Microcontrollers/Question-about-how-to-integrate-ML-model-into-FRDM-MCXN947-by/m-p/1895859#M515</link>
      <description>&lt;P&gt;Hello&amp;nbsp;&lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/230805"&gt;@BillWen&lt;/a&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;There is simple guide demonstrating the steps. Also includes video. Please refer to it:&lt;/P&gt;
&lt;P&gt;&lt;A href="https://www.nxpic.org.cn/module/forum/forum.php?mod=viewthread&amp;amp;tid=803297&amp;amp;page=1&amp;amp;extra=#pid3004813" target="_blank"&gt;https://www.nxpic.org.cn/module/forum/forum.php?mod=viewthread&amp;amp;tid=803297&amp;amp;page=1&amp;amp;extra=#pid3004813&lt;/A&gt;&amp;nbsp;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;BR&lt;/P&gt;
&lt;P&gt;Alice&lt;/P&gt;</description>
      <pubDate>Fri, 28 Jun 2024 10:17:27 GMT</pubDate>
      <guid>https://community.nxp.com/t5/MCX-Microcontrollers/Question-about-how-to-integrate-ML-model-into-FRDM-MCXN947-by/m-p/1895859#M515</guid>
      <dc:creator>Alice_Yang</dc:creator>
      <dc:date>2024-06-28T10:17:27Z</dc:date>
    </item>
    <item>
      <title>Re: Question about how to integrate ML model into FRDM-MCXN947 by tflm_ciar10 project</title>
      <link>https://community.nxp.com/t5/MCX-Microcontrollers/Question-about-how-to-integrate-ML-model-into-FRDM-MCXN947-by/m-p/1897280#M521</link>
      <description>Hello Alice:&lt;BR /&gt;&lt;BR /&gt;First of all. Thanks a lot for your help.&lt;BR /&gt;&lt;BR /&gt;I still don't know why "Label CIFAR10 image programs" without example model for test. I follow the AN14241 application note mentions the converted file "custom_model_converted.tflite", but converted file not provide in SDK.&lt;BR /&gt;&lt;BR /&gt;How to get converted example file or RAW file(before converted)?</description>
      <pubDate>Tue, 02 Jul 2024 07:51:01 GMT</pubDate>
      <guid>https://community.nxp.com/t5/MCX-Microcontrollers/Question-about-how-to-integrate-ML-model-into-FRDM-MCXN947-by/m-p/1897280#M521</guid>
      <dc:creator>BillWen</dc:creator>
      <dc:date>2024-07-02T07:51:01Z</dc:date>
    </item>
  </channel>
</rss>

