How to Train a ConvNet from Scratch

FS Ndzomga
3 min readJun 26, 2023
Photo by Matt Noble on Unsplash

Training a convolutional neural network (ConvNet or CNN) from scratch might sound challenging, especially for newcomers in the field. However, with a structured approach, it becomes a lot easier to understand and implement. In this article, we will go through the process of creating and training a ConvNet from scratch using Python and Keras. The task at hand is to classify images into two categories: ‘cats’ and ‘dogs’.

--

--

FS Ndzomga

Engineer passionate about data science, startups, product management, philosophy and French literature. Built lycee.ai, discute.co and rimbaud.ai