<?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Re: Error while profiling model</title>
    <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1554873#M633</link>
    <description>&lt;P&gt;Hello Hadrien, can you share your model or is it confidential? In order to provide the most efficient support, I need to reproduce your issue.&lt;/P&gt;
&lt;P&gt;Thanks,&lt;/P&gt;
&lt;P&gt;David&lt;/P&gt;</description>
    <pubDate>Wed, 16 Nov 2022 11:27:52 GMT</pubDate>
    <dc:creator>david_piskula</dc:creator>
    <dc:date>2022-11-16T11:27:52Z</dc:date>
    <item>
      <title>Error while profiling model</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1535503#M630</link>
      <description>&lt;P&gt;Hello to all,&lt;/P&gt;&lt;P&gt;I am new to eIQ, and I am trying to profile my own tensorflow model. I can import my model (.tflite or .h5). I checked that the different layers of the CNN were present, but when I launch the profiling, an error appears (see pictures). Unfortunately the error is not very explicit.&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="error_profiling_eiQ.png" style="width: 333px;"&gt;&lt;img src="https://community.nxp.com/t5/image/serverpage/image-id/196397i693326B74474B753/image-size/large?v=v2&amp;amp;px=999" role="button" title="error_profiling_eiQ.png" alt="error_profiling_eiQ.png" /&gt;&lt;/span&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="message_error_profiling_eiQ.png" style="width: 362px;"&gt;&lt;img src="https://community.nxp.com/t5/image/serverpage/image-id/196398iB7C19C8D75F69369/image-size/large?v=v2&amp;amp;px=999" role="button" title="message_error_profiling_eiQ.png" alt="message_error_profiling_eiQ.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;I get the same error as I profile the network:&lt;BR /&gt;- from a .tflite saved with the tensorflow library&lt;BR /&gt;- from a .h5 saved with the tensorflow library&lt;BR /&gt;- from a .tflite saved with eIQ from the loaded .h5&amp;nbsp;&lt;/P&gt;&lt;P&gt;Does anyone have an idea where the error could be coming from?&lt;/P&gt;&lt;P&gt;Thanks in advance,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Tue, 11 Oct 2022 08:57:24 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1535503#M630</guid>
      <dc:creator>Hadrien</dc:creator>
      <dc:date>2022-10-11T08:57:24Z</dc:date>
    </item>
    <item>
      <title>Re: Error while profiling model</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1554873#M633</link>
      <description>&lt;P&gt;Hello Hadrien, can you share your model or is it confidential? In order to provide the most efficient support, I need to reproduce your issue.&lt;/P&gt;
&lt;P&gt;Thanks,&lt;/P&gt;
&lt;P&gt;David&lt;/P&gt;</description>
      <pubDate>Wed, 16 Nov 2022 11:27:52 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1554873#M633</guid>
      <dc:creator>david_piskula</dc:creator>
      <dc:date>2022-11-16T11:27:52Z</dc:date>
    </item>
    <item>
      <title>Re: Error while profiling model</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1565988#M636</link>
      <description>&lt;P&gt;Hello David, thank you for your interest,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Here is a very minimal exemple :&lt;/P&gt;&lt;P&gt;&lt;U&gt;&lt;STRONG&gt;step 1 in python :&lt;/STRONG&gt;&lt;/U&gt;&lt;/P&gt;&lt;P&gt;input1 = tf.keras.layers.Input(shape=(1,1024,4))&lt;/P&gt;&lt;P&gt;x_conv_sep = tf.keras.layers.SeparableConv2D(4,&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; [1,3],&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; strides=(1, 1),&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; padding='same',&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; data_format="channels_last",&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; dilation_rate=(1,1),&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; depth_multiplier=2,&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; use_bias=False,&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; input_shape =[1,1024, 4],&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; depthwise_initializer='he_normal',&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; pointwise_initializer='truncated_normal',&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; name = "conv_dilatation",&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;)(input1)&lt;/P&gt;&lt;P&gt;model.save("conv2d_sep.h5")&lt;/P&gt;&lt;P&gt;&lt;U&gt;&lt;STRONG&gt;step 2 in EIQ:&lt;/STRONG&gt;&lt;/U&gt;&lt;/P&gt;&lt;P&gt;import model&lt;/P&gt;&lt;P&gt;Convert to tflite with quantization (int8) (see picture)&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Hadrien_0-1670424524187.png" style="width: 400px;"&gt;&lt;img src="https://community.nxp.com/t5/image/serverpage/image-id/203388i607596C00BDE862E/image-size/medium?v=v2&amp;amp;px=400" role="button" title="Hadrien_0-1670424524187.png" alt="Hadrien_0-1670424524187.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;import tflite model&amp;nbsp;&lt;/P&gt;&lt;P&gt;try to profile...&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;It seems to be the same as explain in&amp;nbsp; the&amp;nbsp;&lt;FONT size="3"&gt;eIQ Toolkit User Guide 1.5.2 (sec. 4.1) but it doesn't work.&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT size="3"&gt;Do you see where is the problem ?&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;FONT size="3"&gt;Thanks in advance,&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;FONT size="3"&gt;Hadrien&lt;/FONT&gt;&lt;/P&gt;</description>
      <pubDate>Wed, 07 Dec 2022 14:50:04 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1565988#M636</guid>
      <dc:creator>Hadrien</dc:creator>
      <dc:date>2022-12-07T14:50:04Z</dc:date>
    </item>
    <item>
      <title>Re: Error while profiling model</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1568857#M637</link>
      <description>&lt;P&gt;Hello Hadrien,&lt;/P&gt;
&lt;P&gt;I will report this behavior to our developers and let you know what's wrong once they figure it out.&lt;/P&gt;
&lt;P&gt;Thanks,&lt;/P&gt;
&lt;P&gt;David&lt;/P&gt;</description>
      <pubDate>Tue, 13 Dec 2022 08:05:46 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1568857#M637</guid>
      <dc:creator>david_piskula</dc:creator>
      <dc:date>2022-12-13T08:05:46Z</dc:date>
    </item>
    <item>
      <title>Re: Error while profiling model</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1568958#M638</link>
      <description>&lt;P&gt;Thank you for your help&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Hadrien&lt;/P&gt;</description>
      <pubDate>Tue, 13 Dec 2022 10:58:46 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1568958#M638</guid>
      <dc:creator>Hadrien</dc:creator>
      <dc:date>2022-12-13T10:58:46Z</dc:date>
    </item>
    <item>
      <title>Re: Error while profiling model</title>
      <link>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1606062#M655</link>
      <description>&lt;P&gt;Hello &lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/207371"&gt;@Hadrien&lt;/a&gt;, I don't know if the question is still relevant but did you make sure you have the modelrunner application running on your target?&lt;/P&gt;</description>
      <pubDate>Mon, 27 Feb 2023 12:02:25 GMT</pubDate>
      <guid>https://community.nxp.com/t5/eIQ-Machine-Learning-Software/Error-while-profiling-model/m-p/1606062#M655</guid>
      <dc:creator>david_piskula</dc:creator>
      <dc:date>2023-02-27T12:02:25Z</dc:date>
    </item>
  </channel>
</rss>

