<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
        <title>Tensorflow on Nico Maas</title>
        <link>https://www.nico-maas.de/tags/tensorflow/</link>
        <description>Recent content in Tensorflow on Nico Maas</description>
        <generator>Hugo -- gohugo.io</generator>
        <language>en-us</language>
        <lastBuildDate>Mon, 24 Jul 2017 12:00:25 +0000</lastBuildDate><atom:link href="https://www.nico-maas.de/tags/tensorflow/index.xml" rel="self" type="application/rss+xml" /><item>
            <title>CUDA and Tensorflow in Docker</title>
            <link>https://www.nico-maas.de/posts/2017-07-24-cuda-and-tensorflow-in-docker/</link>
            <pubDate>Mon, 24 Jul 2017 12:00:25 +0000</pubDate>
            <guid>https://www.nico-maas.de/posts/2017-07-24-cuda-and-tensorflow-in-docker/</guid>
            <description>&lt;p&gt;In this howto we will get CUDA working in Docker. And - as bonus - add Tensorflow on top! However, please note that you&amp;rsquo;ll need following prereqs:&lt;/p&gt;&#xA;&lt;pre tabindex=&#34;0&#34;&gt;&lt;code&gt;GNU/Linux x86_64 with kernel version &amp;gt; 3.10&#xD;&#xA;Docker &amp;gt;= 1.9 (official docker-engine, docker-ce or docker-ee only)&#xD;&#xA;NVIDIA GPU with Architecture &amp;gt; Fermi (2.1)&#xD;&#xA;NVIDIA drivers &amp;gt;= 340.29 with binary nvidia-modprobe&#xA;&lt;/code&gt;&lt;/pre&gt;&lt;p&gt;We will install the NVIDIA drivers in this tutorial, so you should only have the right kernel and docker version already installed, we&amp;rsquo;re using a Ubuntu 15.05 x64 machine here. For CUDA, you&amp;rsquo;ll need a Fermi 2.1 CUDA card (or better), for tensorflow a &amp;gt;= 3.0 CUDA card&amp;hellip;&lt;/p&gt;</description>
        </item></channel>
</rss>
