<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>npu on Nodjoy</title>
    <link>https://nodjoy.com/tags/npu/</link>
    <description>Recent content in npu on Nodjoy</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <lastBuildDate>Wed, 24 Jun 2026 14:35:20 +0800</lastBuildDate><atom:link href="https://nodjoy.com/tags/npu/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>瑞芯微RK3588配置yolo环境</title>
      <link>https://nodjoy.com/note/20260624/rknn.html</link>
      <pubDate>Wed, 24 Jun 2026 14:35:20 +0800</pubDate>
      
      <guid>https://nodjoy.com/note/20260624/rknn.html</guid>
      <description>环境 Ubuntu 22.04-local(x86-64) Ubuntu 22.04-rk3588(aarch64) RK3588 python3.8 本机-x86-64 配置rknn-toolkit2环境 conda create -n rknn python=3.8 conda activate rknn pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple # reference: https://github.com/rockchip-linux/rknn-toolkit2 wget https://ghfast.top/github.com/airockchip/rknn-toolkit2/blob/master/rknn-toolkit2/packages/x86_64/requirements_cp38-2.3.2.txt pip install -r requirements_cp38-2.3.2.txt wget https://ghfast.top/github.com/airockchip/rknn-toolkit2/blob/master/rknn-toolkit2/packages/x86_64/rknn_toolkit2-2.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl pip install rknn_toolkit2-2.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl git clone https://github.com/airockchip/ultralytics_yolov8.git cd ultralytics_yolov8 pip install -e .</description>
    </item>
    
  </channel>
</rss>
