<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>技术探索 - 分类 | 飞污熊小站</title><link>https://xiongneng.me/categories/%E6%8A%80%E6%9C%AF%E6%8E%A2%E7%B4%A2/</link><description>飞污熊小站</description><generator>Hugo 0.166.0 &amp; FixIt v0.4.6-20260512073637-464c4659</generator><language>zh-CN</language><managingEditor>yidao620@163.com (XiongNeng)</managingEditor><webMaster>yidao620@163.com (XiongNeng)</webMaster><copyright>XiongNeng</copyright><lastBuildDate>Fri, 25 Sep 2026 01:57:03 +0000</lastBuildDate><atom:link href="https://xiongneng.me/categories/%E6%8A%80%E6%9C%AF%E6%8E%A2%E7%B4%A2/index.xml" rel="self" type="application/rss+xml"/><item><title>Supervision：一个Python库写尽所有视觉工具</title><link>https://xiongneng.me/posts/explore/supervision/</link><pubDate>Fri, 25 Sep 2026 09:46:45 +0800</pubDate><author>yidao620@163.com (XiongNeng)</author><guid>https://xiongneng.me/posts/explore/supervision/</guid><category domain="https://xiongneng.me/categories/%E6%8A%80%E6%9C%AF%E6%8E%A2%E7%B4%A2/">技术探索</category><description>&lt;p&gt;你是否也经历过这些令人头疼的“造轮子”时刻：训练好了一个目标检测模型，却还要花半天写代码在图像上画框、标类别、调颜色；想统计视频里的人数或车辆，结果大部分时间都耗在了追踪算法的调试和区域计数逻辑上；换个模型试试效果，之前为标注和数据加载写的那套代码又得全部推倒重来。&lt;/p&gt;</description></item></channel></rss>