<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Metrics on TPOW Lab</title><link>https://tpow-001.netlify.app/tags/metrics/</link><description>Recent content in Metrics on TPOW Lab</description><generator>Hugo</generator><language>en</language><copyright>Copyright &amp;copy; 2025-2026 TPOW-001. All Rights Reserved.</copyright><lastBuildDate>Mon, 18 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://tpow-001.netlify.app/tags/metrics/index.xml" rel="self" type="application/rss+xml"/><item><title>supervision 完整教學 — Roboflow 開源 Computer Vision 工具集從零到上線</title><link>https://tpow-001.netlify.app/post/2026-05-18-supervision-tutorial/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://tpow-001.netlify.app/post/2026-05-18-supervision-tutorial/</guid><description><![CDATA[<h1 id="supervision-完整教學" data-numberify>supervision 完整教學<a class="anchor ms-1" href="#supervision-完整教學"></a></h1>
<blockquote>
<p>30 分鐘從安裝到能寫出「車流計數 / 區域進出告警 / 速度估計」這類 production 級 CV pipeline。</p></blockquote>
<hr>

<h2 id="1-專案定位" data-numberify>1. 專案定位<a class="anchor ms-1" href="#1-專案定位"></a></h2>

<h3 id="11-一句話總結" data-numberify>1.1 一句話總結<a class="anchor ms-1" href="#11-一句話總結"></a></h3>
<p><strong><code>supervision</code></strong> 是 <a href="https://roboflow.com" target="_blank" rel="noopener noreferrer">Roboflow<i class="fas fa-external-link-square-alt ms-1"></i></a> 開源的 <strong>model-agnostic</strong> computer vision toolkit。把任何 detection / segmentation / classification model 的輸出 <strong>標準化</strong> 成統一資料結構（<code>sv.Detections</code> / <code>sv.KeyPoints</code> / <code>sv.Classifications</code>），然後用一套乾淨 API 做視覺化、ROI 計數、速度估算、tracking、dataset 轉換、metric 計算。</p>]]></description></item></channel></rss>