<?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 Jeroen Nyckees</title><link>https://jenyckee.github.io/tags/tensorflow/</link><description>Recent content in TensorFlow on Jeroen Nyckees</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 01 Feb 2020 10:55:30 +0100</lastBuildDate><atom:link href="https://jenyckee.github.io/tags/tensorflow/index.xml" rel="self" type="application/rss+xml"/><item><title>Grand Place people and car detection</title><link>https://jenyckee.github.io/posts/grand-place/</link><pubDate>Sat, 01 Feb 2020 10:55:30 +0100</pubDate><guid>https://jenyckee.github.io/posts/grand-place/</guid><description>&lt;p>On &lt;a href="http://www.brussel.be/webcam-grote-markt">http://www.brussel.be/webcam-grote-markt&lt;/a> you can find a webcam stream of the Grand Place in Brussels. When I saw this I was wondering if I could build a model to trace individual people and eventually track their behaviour while walking on one of the most touristy spots in Brussels.&lt;/p>
&lt;p>I set up a website with TensorFlow.js using the &lt;a href="https://github.com/tensorflow/tfjs-models/tree/master/coco-ssd">coco-ssd&lt;/a> model but was slightly dissapointed with the results. After doing some more research I read about transfer learning and decided to try and improve model.&lt;/p></description></item></channel></rss>