<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Deep-Learning on Drentin's Findings</title><link>https://drentin.au/tags/deep-learning/</link><description>Recent content in Deep-Learning on Drentin's Findings</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 15 Sep 2021 01:00:00 +1000</lastBuildDate><atom:link href="https://drentin.au/tags/deep-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>ML with an AWS DeepLens: Compost, Landfill or Recycling..?</title><link>https://drentin.au/posts/compost-landfill-recycling/</link><pubDate>Wed, 15 Sep 2021 01:00:00 +1000</pubDate><guid>https://drentin.au/posts/compost-landfill-recycling/</guid><description>&lt;h1 id="what-we-all-came-here-for-sagemaker"&gt;What we all came here for&amp;hellip; SageMaker!&lt;/h1&gt;
&lt;p&gt;I was excited to get stuck into &lt;a href="https://www.awsdeeplens.recipes/400_advanced/410_trash_sorter/"&gt;the Advanced recipe - Build a custom ML model to sort trash&lt;/a&gt; as this started getting into the parts I wanted to know more about; how to get a basic model trained in SageMaker and then deploy it to the DeepLens device.&lt;/p&gt;
&lt;h1 id="step-1---train"&gt;Step 1 - Train!&lt;/h1&gt;
&lt;p&gt;Luckily in this example they include a number of sample images, quite a decent set really with over 500 images in total, separated into Compost, Landfill and Recycling.&lt;/p&gt;</description></item></channel></rss>