<?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のトピックDepthToSpace not working on IMX.8M plus</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/DepthToSpace-not-working-on-IMX-8M-plus/m-p/1979266#M229982</link>
    <description>&lt;P&gt;Hi I'm trying to run a model with a depth2space with the vx delegate and I'm getting the following error:&amp;nbsp;&lt;/P&gt;&lt;P&gt;ERROR: Int8 or uint8 input without quantization is not supported in Depth2Space&lt;BR /&gt;INFO: Created TensorFlow Lite XNNPACK delegate for CPU.&lt;BR /&gt;E [/usr/src/debug/tim-vx/1.2.2/src/tim/vx/internal/src/ops/vsi_nn_op_gather.c:op_check:156]Inputs/Outputs data type not support: ASYM UINT8, INT32, INT8&lt;BR /&gt;E [/usr/src/debug/tim-vx/1.2.2/src/tim/vx/internal/src/vsi_nn_graph.c:setup_node:551]Check node[0] GATHER fail&lt;BR /&gt;&lt;BR /&gt;This is the graph:&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="spacy_2-1729602849179.png" style="width: 400px;"&gt;&lt;img src="https://community.nxp.com/t5/image/serverpage/image-id/306162i396753DB57CE9652/image-size/medium?v=v2&amp;amp;px=400" role="button" title="spacy_2-1729602849179.png" alt="spacy_2-1729602849179.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;Everything is in int8.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Tue, 22 Oct 2024 13:19:13 GMT</pubDate>
    <dc:creator>spacy</dc:creator>
    <dc:date>2024-10-22T13:19:13Z</dc:date>
    <item>
      <title>DepthToSpace not working on IMX.8M plus</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/DepthToSpace-not-working-on-IMX-8M-plus/m-p/1979266#M229982</link>
      <description>&lt;P&gt;Hi I'm trying to run a model with a depth2space with the vx delegate and I'm getting the following error:&amp;nbsp;&lt;/P&gt;&lt;P&gt;ERROR: Int8 or uint8 input without quantization is not supported in Depth2Space&lt;BR /&gt;INFO: Created TensorFlow Lite XNNPACK delegate for CPU.&lt;BR /&gt;E [/usr/src/debug/tim-vx/1.2.2/src/tim/vx/internal/src/ops/vsi_nn_op_gather.c:op_check:156]Inputs/Outputs data type not support: ASYM UINT8, INT32, INT8&lt;BR /&gt;E [/usr/src/debug/tim-vx/1.2.2/src/tim/vx/internal/src/vsi_nn_graph.c:setup_node:551]Check node[0] GATHER fail&lt;BR /&gt;&lt;BR /&gt;This is the graph:&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="spacy_2-1729602849179.png" style="width: 400px;"&gt;&lt;img src="https://community.nxp.com/t5/image/serverpage/image-id/306162i396753DB57CE9652/image-size/medium?v=v2&amp;amp;px=400" role="button" title="spacy_2-1729602849179.png" alt="spacy_2-1729602849179.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;Everything is in int8.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Tue, 22 Oct 2024 13:19:13 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/DepthToSpace-not-working-on-IMX-8M-plus/m-p/1979266#M229982</guid>
      <dc:creator>spacy</dc:creator>
      <dc:date>2024-10-22T13:19:13Z</dc:date>
    </item>
    <item>
      <title>Re: DepthToSpace not working on IMX.8M plus</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/DepthToSpace-not-working-on-IMX-8M-plus/m-p/1980241#M230048</link>
      <description>&lt;P&gt;Hello,&lt;/P&gt;
&lt;P&gt;Check your eIQ your screen shot look like&amp;nbsp; is for i.MXRT, DepthToSpace is not supported in i.MX8&lt;/P&gt;
&lt;P&gt;Regards&lt;/P&gt;</description>
      <pubDate>Wed, 23 Oct 2024 13:42:16 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/DepthToSpace-not-working-on-IMX-8M-plus/m-p/1980241#M230048</guid>
      <dc:creator>Bio_TICFSL</dc:creator>
      <dc:date>2024-10-23T13:42:16Z</dc:date>
    </item>
  </channel>
</rss>

