<?xml version="1.0" encoding="utf-8" ?><rss version="2.0" xmlns:tt="http://teletype.in/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>@alg</title><generator>teletype.in</generator><description><![CDATA[@alg]]></description><image><url>https://teletype.in/files/e2/ab/e2ab4bef-6bf4-48a0-b391-5e8084ac1bca.jpeg</url><title>@alg</title><link>https://teletype.in/@alg</link></image><link>https://teletype.in/@alg?utm_source=teletype&amp;utm_medium=feed_rss&amp;utm_campaign=alg</link><atom:link rel="self" type="application/rss+xml" href="https://teletype.in/rss/alg?offset=0"></atom:link><atom:link rel="next" type="application/rss+xml" href="https://teletype.in/rss/alg?offset=10"></atom:link><atom:link rel="search" type="application/opensearchdescription+xml" title="Teletype" href="https://teletype.in/opensearch.xml"></atom:link><pubDate>Sat, 02 May 2026 09:34:28 GMT</pubDate><lastBuildDate>Sat, 02 May 2026 09:34:28 GMT</lastBuildDate><item><guid isPermaLink="true">https://teletype.in/@alg/imagecluster</guid><link>https://teletype.in/@alg/imagecluster?utm_source=teletype&amp;utm_medium=feed_rss&amp;utm_campaign=alg</link><comments>https://teletype.in/@alg/imagecluster?utm_source=teletype&amp;utm_medium=feed_rss&amp;utm_campaign=alg#comments</comments><dc:creator>alg</dc:creator><title>Image clustering</title><pubDate>Fri, 08 May 2020 11:24:34 GMT</pubDate><media:content medium="image" url="https://teletype.in/files/e1/b5/e1b503a3-e695-4f2c-ac6c-2607ca04767b.png"></media:content><description><![CDATA[<img src="https://teletype.in/files/82/a2/82a2bf21-a873-490b-bbcf-ee8f2b99bdc4.png"></img>I've used https://github.com/elcorto/imagecluster. It computes neural feature vector via VGG16. Uses around 100G RAM for 20k photos. Works OK on cpu, if you have like 16 of them.]]></description><content:encoded><![CDATA[
  <figure class="m_original">
    <img src="https://teletype.in/files/82/a2/82a2bf21-a873-490b-bbcf-ee8f2b99bdc4.png" width="815" />
    <figcaption>Thanks to all the people on social networks, who put much effort organized images into nice datasets on every imaginable topic</figcaption>
  </figure>
  <p>I&#x27;ve used <a href="https://github.com/elcorto/imagecluster" target="_blank">https://github.com/elcorto/imagecluster.</a> It computes neural feature vector via VGG16. Uses around 100G RAM for 20k photos. Works OK on cpu, if you have like 16 of them.</p>
  <p>For clustering, sqeuclidean metric worked best for me. </p>
  <p>There&#x27;s also <a href="https://github.com/facebookresearch/deepcluster" target="_blank">https://github.com/facebookresearch/deepcluster,</a> but all it did for me is mess with CUDA and crash.</p>
  <p>Bonus picture from dataset</p>
  <figure class="m_original">
    <img src="https://teletype.in/files/74/4f/744f13f8-5568-48aa-9ff7-8b77420d5004.png" width="1024" />
  </figure>

]]></content:encoded></item></channel></rss>