<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Regarding the abnormal operation of main&#x2F;face_detector.cpp published in UnitV2Framework]]></title><description><![CDATA[<p dir="auto">When I built and ran "main/face_detector.cpp" published in <a href="https://github.com/m5stack/UnitV2Framework" target="_blank" rel="noopener noreferrer nofollow ugc">UnitV2Framework</a>, the image update in "<a href="http://unitv2.py" target="_blank" rel="noopener noreferrer nofollow ugc">http://unitv2.py</a>" took more than a few minutes and was not practical. The "face_detector" in the factory-shipped M5stack UnitV2 updates the image almost in real time.<br />
What we are currently checking is that the value of "faceobjects.size()" on the 74th line of "face_detector.cpp" is large and the processing is expected to be heavy.<br />
I would like to know how to solve this problem.</p>
]]></description><link>https://community.m5stack.com/topic/4703/regarding-the-abnormal-operation-of-main-face_detector-cpp-published-in-unitv2framework</link><generator>RSS for Node</generator><lastBuildDate>Fri, 15 May 2026 16:55:01 GMT</lastBuildDate><atom:link href="https://community.m5stack.com/topic/4703.rss" rel="self" type="application/rss+xml"/><pubDate>Thu, 13 Oct 2022 18:54:46 GMT</pubDate><ttl>60</ttl></channel></rss>