Member-only story

How to build a simple CNN based Image classifier using Keras

Milind Soorya
Analytics Vidhya
Published in
3 min readJun 1, 2022

1 Introduction

1.1 What are Convolutional neural networks (CNN)?

Convolutional neural network (CNN), are a class of artificial neural networks that has become dominant in various computer vision tasks, it is attracting interest across a variety of domains.

A convolutional neural network is composed of multiple building blocks, such as convolution layers, pooling layers, and fully connected layers, and is designed to automatically and adaptively learn spatial hierarchies of features through a back propagation algorithm.

CNN work well on computer vision tasks like image classification, object detection, image recognition, etc. Other Neural networks used for similar tasks includes recurrent neural networks (RNN), long short term memory (LSTM), artificial neural networks (ANN), etc.,

1.2 The classification task

In this article, I will be trying to solve the HP Unlocked challenge. It is challenge number four.

You can get the data from the above website, or you could also fork the files from my GitHub repository — Unlocked_Challenge_4 and start working on it directly.

1.3 Problem statement

--

--

Analytics Vidhya
Analytics Vidhya

Published in Analytics Vidhya

Analytics Vidhya is a community of Generative AI and Data Science professionals. We are building the next-gen data science ecosystem https://www.analyticsvidhya.com

Milind Soorya
Milind Soorya

Written by Milind Soorya

Interested in Deep Learning, Machine Learning, Data Science, Web development? Checkout my blog: https://milindsoorya.co.uk/

Responses (1)