<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>模型转换 on 111qqz's blog</title><link>https://111qqz.com/en/tags/%E6%A8%A1%E5%9E%8B%E8%BD%AC%E6%8D%A2/</link><description>Recent content in 模型转换 on 111qqz's blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2015-2026 111qqz</copyright><lastBuildDate>Fri, 18 Sep 2020 11:02:50 +0800</lastBuildDate><atom:link href="https://111qqz.com/en/tags/%E6%A8%A1%E5%9E%8B%E8%BD%AC%E6%8D%A2/index.xml" rel="self" type="application/rss+xml"/><item><title>【施工中】torch2trt　学习笔记</title><link>https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2020-09-18-torch2trt-notes/</link><pubDate>Fri, 18 Sep 2020 11:02:50 +0800</pubDate><guid>https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2020-09-18-torch2trt-notes/</guid><description>&lt;h2 class="relative group"&gt;前言
 &lt;div id="前言" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#%e5%89%8d%e8%a8%80" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;偶然发现了 &lt;a href="https://github.com/NVIDIA-AI-IOT/torch2trt" target="_blank" rel="noreferrer"&gt;torch2trt&lt;/a&gt; 的模型转换方案，思路是直接将pytorch op映射到TensorRT的python api. 在pytorch进行每个op　forward的时候，tensorrt也相应往network上添加op.
这里会先涉及torch2trt的使用，后面会补充这个转换工具的代码学习&lt;/p&gt;</description></item></channel></rss>