<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Callbacks on AI VOID</title><link>https://ai-blog.noorshomelab.dev/tags/callbacks/</link><description>Recent content in Callbacks on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 26 Oct 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/tags/callbacks/index.xml" rel="self" type="application/rss+xml"/><item><title>TensorFlow Guide: Intermediate Topics - Custom Training Loops and Callbacks</title><link>https://ai-blog.noorshomelab.dev/tensorflow-guide/intermediate-tensorflow-custom-training-loops-callbacks/</link><pubDate>Sun, 26 Oct 2025 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/tensorflow-guide/intermediate-tensorflow-custom-training-loops-callbacks/</guid><description>&lt;h2 id="5-intermediate-topics"&gt;5. Intermediate Topics&lt;/h2&gt;
&lt;p&gt;While &lt;code&gt;model.fit()&lt;/code&gt; is incredibly convenient, sometimes you need more control over the training process. This chapter introduces two powerful intermediate topics: &lt;strong&gt;Custom Training Loops&lt;/strong&gt; for ultimate flexibility and &lt;strong&gt;Keras Callbacks&lt;/strong&gt; for customizing &lt;code&gt;model.fit()&lt;/code&gt; behavior.&lt;/p&gt;
&lt;h3 id="51-custom-training-loops-with-tfgradienttape"&gt;5.1 Custom Training Loops with &lt;code&gt;tf.GradientTape&lt;/code&gt;&lt;/h3&gt;
&lt;p&gt;A custom training loop gives you full control over every aspect of the training process, from calculating gradients to updating model weights. This is particularly useful for:&lt;/p&gt;</description></item></channel></rss>