<?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Re: About OpenVX Graph Cache</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/About-OpenVX-Graph-Cache/m-p/1433286#M188564</link>
    <description>&lt;P&gt;&lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/151788"&gt;@Zhiming_Liu&lt;/a&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;thaks for your reply.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I'm using library based on gatesgarth-5.10.9-1.0.0&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks.&lt;/P&gt;</description>
    <pubDate>Thu, 24 Mar 2022 08:16:37 GMT</pubDate>
    <dc:creator>at_akihito</dc:creator>
    <dc:date>2022-03-24T08:16:37Z</dc:date>
    <item>
      <title>About OpenVX Graph Cache</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/About-OpenVX-Graph-Cache/m-p/1428905#M188256</link>
      <description>&lt;P&gt;Hi.&lt;/P&gt;&lt;P&gt;I'm using a board with i.MX8MPlus.&lt;/P&gt;&lt;P&gt;I have created a model and a Python script to segment humans from captured images using machine learning.&lt;/P&gt;&lt;P&gt;I tried the OpenVX graph cache to reduce the warm-up time before running the inference, but it stopped working on the second and subsequent runs.&lt;/P&gt;&lt;P&gt;I'm attaching the source code and model that reproduces the situation.&lt;/P&gt;&lt;P&gt;logs from the run are as follows:&lt;/P&gt;&lt;LI-CODE lang="markup"&gt;# tar xf cache_error.tar.gz
# cd image_segmentation
# export VIV_VX_ENABLE_CACHE_GRAPH_BINARY="1"                                                      
# export VIV_VX_CACHE_BINARY_GRAPH_DIR=`pwd`
# python3 image_segmentation.py
INFO: Created TensorFlow Lite delegate for NNAPI.
WARNING: Operator RESIZE_BILINEAR (v2) refused by NNAPI delegate: Operator refused due performance reasons.
WARNING: Operator RESIZE_BILINEAR (v2) refused by NNAPI delegate: Operator refused due performance reasons.
WARNING: Operator RESIZE_BILINEAR (v2) refused by NNAPI delegate: Operator refused due performance reasons.
WARNING: Operator RESIZE_BILINEAR (v2) refused by NNAPI delegate: Operator refused due performance reasons.
Applied NNAPI delegate.

# ls *.nb
7defa710c26bc71d88b66e629b41d231.nb  883db2f3bfce82bede17e5bed2e4a6b5.nb  ca661c9048851a6b2755fa0982d07102.nb
# python3 image_segmentation.py
INFO: Created TensorFlow Lite delegate for NNAPI.
WARNING: Operator RESIZE_BILINEAR (v2) refused by NNAPI delegate: Operator refused due performance reasons.
WARNING: Operator RESIZE_BILINEAR (v2) refused by NNAPI delegate: Operator refused due performance reasons.
WARNING: Operator RESIZE_BILINEAR (v2) refused by NNAPI delegate: Operator refused due performance reasons.
WARNING: Operator RESIZE_BILINEAR (v2) refused by NNAPI delegate: Operator refused due performance reasons.
Applied NNAPI delegate.  # &amp;lt;- freeze&lt;/LI-CODE&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks.&lt;/P&gt;</description>
      <pubDate>Wed, 16 Mar 2022 02:45:00 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/About-OpenVX-Graph-Cache/m-p/1428905#M188256</guid>
      <dc:creator>at_akihito</dc:creator>
      <dc:date>2022-03-16T02:45:00Z</dc:date>
    </item>
    <item>
      <title>Re: About OpenVX Graph Cache</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/About-OpenVX-Graph-Cache/m-p/1431021#M188404</link>
      <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/197692"&gt;@at_akihito&lt;/a&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Which bsp you use?&lt;/P&gt;
&lt;P&gt;I tried it on L5.10.72_2.2.0,fail to use NNAPI even i use&amp;nbsp;libvx_delegate in code.&lt;/P&gt;
&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="nxf65025_0-1647832846294.png" style="width: 400px;"&gt;&lt;img src="https://community.nxp.com/t5/image/serverpage/image-id/174212iEA1EB63409C3140B/image-size/medium?v=v2&amp;amp;px=400" role="button" title="nxf65025_0-1647832846294.png" alt="nxf65025_0-1647832846294.png" /&gt;&lt;/span&gt;&lt;/P&gt;
&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="nxf65025_1-1647832872001.png" style="width: 400px;"&gt;&lt;img src="https://community.nxp.com/t5/image/serverpage/image-id/174213i574EB8B292410B4C/image-size/medium?v=v2&amp;amp;px=400" role="button" title="nxf65025_1-1647832872001.png" alt="nxf65025_1-1647832872001.png" /&gt;&lt;/span&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="nxf65025_3-1647832997215.png" style="width: 400px;"&gt;&lt;img src="https://community.nxp.com/t5/image/serverpage/image-id/174215iE86E2C26BBB72CD8/image-size/medium?v=v2&amp;amp;px=400" role="button" title="nxf65025_3-1647832997215.png" alt="nxf65025_3-1647832997215.png" /&gt;&lt;/span&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 21 Mar 2022 03:23:31 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/About-OpenVX-Graph-Cache/m-p/1431021#M188404</guid>
      <dc:creator>Zhiming_Liu</dc:creator>
      <dc:date>2022-03-21T03:23:31Z</dc:date>
    </item>
    <item>
      <title>Re: About OpenVX Graph Cache</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/About-OpenVX-Graph-Cache/m-p/1433286#M188564</link>
      <description>&lt;P&gt;&lt;a href="https://community.nxp.com/t5/user/viewprofilepage/user-id/151788"&gt;@Zhiming_Liu&lt;/a&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;thaks for your reply.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I'm using library based on gatesgarth-5.10.9-1.0.0&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks.&lt;/P&gt;</description>
      <pubDate>Thu, 24 Mar 2022 08:16:37 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/About-OpenVX-Graph-Cache/m-p/1433286#M188564</guid>
      <dc:creator>at_akihito</dc:creator>
      <dc:date>2022-03-24T08:16:37Z</dc:date>
    </item>
  </channel>
</rss>

