Image Classification using Deep Learning & PyTorch: A Case Study with Flower Image Data

Author(s): Avishek Nag

Originally published on Towards AI.

Classifying Flower images using Convolutional Deep Neural Network with PyTorch library

Photo by Krystina rogers on Unsplash

Classifying image data is one of the very popular usages of Deep Learning techniques. In this article, we will discuss the identification of flower images using a deep convolutional neural network.

For this, we will be using PyTorch, TorchVision & PIL libraries of Python

The required dataset for this problem can be found at Kaggle. It contains a folder structure & flower images inside it. There are 5 different types of flowers. The folder structure looks like below

Fig 1

Now, we will see a sample of the flower image from folder ‘rose’

show_image("../data/flowers/rose/537207677_f96a0507bb.jpg")

PyTorch always expects data in the form… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI