Image Classification Part 1

Hello Internet World! Back with an exciting topic!

Recent advances in deep learning made tasks such as Image and speech recognition possible. Most people talk about these days whilst discussing machine learning / deep learning is Tensorflow and Neural Networks. Deep Learning is nothing but a subset of Machine Learning Algorithms which is specifically good at recognizing patterns but typically requires a large number of data.

This post describes a Keras based Convolution Neural Net for image classification from scratch. There are several scripts which use pre-trained models available for image classification such as Google’s Inception model. The objective of this project was to classify Mountain Bike and Road Bikes.

I have attached the resources used for the completion of this project. The links below explain the information vital for creating your very own image classification model using tensorflow Keras library. Also,check out my project description here.

The following links were greatly helpful for the completion of this project:

• Tensorflow Tutorials
• Keras Basic Classification
• Activation Functions
• Loss Function

Referred to this GitHub repository and YouTube video:

• Tensorflow Image Classification Github Repository with Inception Model
• Tensorflow Image Classification Youtube link with Inception Model

So what are you waiting for, go create your very own CNN image classifier! Let me know in the comments your questions and your model results!

Thanks!!

Shreyas

Written on February 17, 2019