Build A Handwriting Recognizer In Python

I presented this webinar in 2018 for the students in my machine learning bootcamp.

In the webinar you’ll see me develop a handwriting recognition app in Python that automatically transcribes the handwritten digits of the MNIST dataset to digitized text. I will be using the Tensorflow library.

1 ¼ Hours



Webinar Contents

Introducing Machine Learning

Current trends in AI

Jobs replaced by robots

Machine learning algorithms

The convolutional neural network

Introducing Tensorflow

The Tensorflow library

Using Python in Visual Studio

Dense Neural networks

The neural network we’re going to use

The MNIST Dataset

A dataset of handwritten digits

The image format

Reading the dataset with Python

The Code

Numpy, Pandas and Tensorflow

Reading and processing the dataset

Shaping the tensors

The training function

Calculating training & validation loss

The Results

Demo: training the neural network

The trainng & validation loss graphs

The confusion matrix

Testing the fully trained model

The Testing App

The WinForms app

Sampling a handwritten digit

Calling Python to get a prediction

Demo: testing the app

Watch The Webinar

Ready For More?


Did I pique your interest? Then check out all of my AI training courses and get ready to supercharge your machine learning career today. See anything that you like?

Download The Source Code

Would you like to experiment with your own code? Just click the button to download the exact same source code that I use in the webinar. Use my code as a starting point to develop your own C# computer vision applications!


what my students are saying about ME