<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[SnoopyBUG的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/SnoopyBUG</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; SnoopyBUG]]></copyright><item><title><![CDATA[PyTorch构造数据集（深度学习计算机视觉）]]></title><link>https://blog.youkuaiyun.com/SnoopyBUG/article/details/119334812</link><guid>https://blog.youkuaiyun.com/SnoopyBUG/article/details/119334812</guid><author>SnoopyBUG</author><pubDate>Mon, 02 Aug 2021 23:17:30 +0800</pubDate><description><![CDATA[PyTorch构造数据集（深度学习计算机视觉）。PyTorch下构造图片数据集。步骤包括：创建合适的文本文件（包含每一张图片的路径与标签）、自定义Dataset的子类datasets，利用DataLoader生成训练和测试数据集。]]></description><category></category></item><item><title><![CDATA[深度卷积神经网络在CPU上计算的加速]]></title><link>https://blog.youkuaiyun.com/SnoopyBUG/article/details/118532560</link><guid>https://blog.youkuaiyun.com/SnoopyBUG/article/details/118532560</guid><author>SnoopyBUG</author><pubDate>Wed, 07 Jul 2021 09:50:50 +0800</pubDate><description><![CDATA[深度卷积神经网络在CPU上计算的加速。在利用MXNet对AlexNet简化模拟实现过程中，由于机器没独显，只能利用在CPU进行计算，但计算时间过长。解决思路有两个：优化读取数据的函数，Intel MKL-DNN加速深度神经网络计算。]]></description><category></category></item></channel></rss>