<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>MobileNetV2 | Maaz Salman</title><link>https://maazsalman.com/tags/mobilenetv2/</link><atom:link href="https://maazsalman.com/tags/mobilenetv2/index.xml" rel="self" type="application/rss+xml"/><description>MobileNetV2</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sun, 02 Jan 2022 00:00:00 +0000</lastBuildDate><image><url>https://maazsalman.com/media/icon_hub75224e924a801dac222e2220d610f2c_32468_512x512_fill_lanczos_center_3.png</url><title>MobileNetV2</title><link>https://maazsalman.com/tags/mobilenetv2/</link></image><item><title>Train-MobileNet for TinyML</title><link>https://maazsalman.com/project/train-mobilenet/</link><pubDate>Sun, 02 Jan 2022 00:00:00 +0000</pubDate><guid>https://maazsalman.com/project/train-mobilenet/</guid><description>&lt;h2 id="-project-overview">🔬 Project Overview&lt;/h2>
&lt;p>This code is a script for training an image classification model MobileNet using PyTorch. The code is structured to facilitate easy training, evaluation, and monitoring of a deep learning model for image classification. It allows for periodic saving of the model&amp;rsquo;s state and provides insights into the model&amp;rsquo;s performance through loss curves and accuracy metrics.
The repo also contains a script which is designed to process time series data from CSV files and generate Continuous Wavelet Transform (CWT) spectrograms for each column in the data. It&amp;rsquo;s typically used for signal analysis, particularly in scenarios involving time-frequency representation of signals.&lt;/p>
&lt;p>&lt;em>(For full source code, pin configurations, and implementation details, please view the GitHub repository using the button above).&lt;/em>&lt;/p></description></item></channel></rss>