About this project
This project is Capstone project for the course "Getting started with tensorflow 2" offered by Imperial College London on Coursera. The project is about SVHN dataset. This is an image dataset of over 600,000 digit images in all, and is a harder dataset than MNIST as the numbers appear in the context of natural scene images. SVHN is obtained from house numbers in Google Street View images. In this notebook, I created a neural network that classifies real-world images digits. I used concepts from throughout this course in building, training, testing, validating and saving Tensor.
More projects by Akriti Sood
Goodreads - Web Scraping using Beautiful Soup
A mug of coffee and my favorite novel, an ideal day for me. But deciding which novel to read is...
Heart rate prediction using Logistic Regression
World Health Organization has estimated 12 million deaths occur worldwide, every year due to...