<?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 avanwyk</title>
    <link>https://avanwyk.com/tag/tensorflow/</link>
    <description>Recent content in TensorFlow on avanwyk</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <managingEditor>andrich@avanwyk.com (Andrich van Wyk)</managingEditor>
    <webMaster>andrich@avanwyk.com (Andrich van Wyk)</webMaster>
    <copyright>© 2026 Andrich van Wyk</copyright>
    <lastBuildDate>Mon, 02 Sep 2019 21:45:00 +0000</lastBuildDate><atom:link href="https://avanwyk.com/tag/tensorflow/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>Super-convergence in Tensorflow 2 with the 1Cycle Policy</title>
      <link>https://avanwyk.com/tensorflow-2-super-convergence-with-the-1cycle-policy/</link>
      <pubDate>Mon, 02 Sep 2019 21:45:00 +0000</pubDate>
      <author>andrich@avanwyk.com (Andrich van Wyk)</author>
      <guid>https://avanwyk.com/tensorflow-2-super-convergence-with-the-1cycle-policy/</guid>
      <description>Implementing super-convergence for deep neural network training in Tensorflow 2 with the 1Cycle learning rate policy.</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://avanwyk.com/tensorflow-2-super-convergence-with-the-1cycle-policy/feature.jpg" />
    </item>
    
    <item>
      <title>Finding a Learning Rate with Tensorflow 2</title>
      <link>https://avanwyk.com/finding-a-learning-rate-in-tensorflow-2/</link>
      <pubDate>Sun, 28 Jul 2019 11:05:37 +0000</pubDate>
      <author>andrich@avanwyk.com (Andrich van Wyk)</author>
      <guid>https://avanwyk.com/finding-a-learning-rate-in-tensorflow-2/</guid>
      <description>Implementing the technique in Tensorflow 2 is straightforward. Start from a low learning rate, increase the learning rate and record the loss. Stop when a very high learning rate is reached. Plot the losses and learning rates choosing a learning rate where the loss is decreasing at a rapid rate.</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://avanwyk.com/finding-a-learning-rate-in-tensorflow-2/feature.jpeg" />
    </item>
    
  </channel>
</rss>
