I’m Theo Clark and these are some of the projects I’ve been working on recently. My work has focused on Deep Learning and most projects involve models built using PyTorch, mainly for computer vision tasks with a particular focus on Generative Adversarial Networks. To see the code and experiment with them yourself then head to my GitHub profile. If anything interests you and you’d like to reach out then please contact me using the links at the bottom of the page.
![Profile Picture](./images/profile.png)
Welcome
Projects
Build a Neural Net in Numpy
![Neural Network GIF](./images/nnn_icon.gif)
Build a neural network from scratch in Numpy. PyTorch and Tensorflow are super convenient but building up a neural network from scratch in Numpy is a great exercise and can help to explain what's going on under the hood.
Read the post | Visit the repo
Sign Language interpreter
![Sign Language Example GIF](./images/sign-language-example.gif)
An app to read the American Sign Language alphabet. Built using a simple ConvNet in PyTorch. Trained on a new dataset (available below) designed to increase the variability of images. Clone or Download the repo to explore the app yourself.
Read the post | Visit the repo | Download dataset
CycleGAN: paint like Monet
![Sign Language Example GIF](./images/SampleImages.png)
App to convert landscape photos into Monet style paintings using an implementation of CycleGAN in PyTorch. Have a go at converting your own landscape image to Monet-style paintings using an app I built using Heroku and Flask.
Read the post | Visit the repo | Try it out
Wasserstein GANs: create handwritten digits
![Sign Language Example GIF](./images/generated_digits.png)
Model to generate handwritten digits. The PyTorch model is trained on MNIST and is based on a Wasserstein General Adversarial Network with Gradient Penalty (WGAN-GP). Clone or Download the repository to generate your own handwritten digits.
Read the post | Visit the repo
Other Posts
New to Machine Learning and wondering how to get started? For an overview of the important theoretical ideas and an introduction to writing ML code read how to get started with Machine Learning. There are lots of additional links provided to take you further.
Interested in Neural Networks and want to understand the basics of how they operate? For an introduction to the main steps involved in training a model start here.
Wondering which loss function to use? Not sure how to use a loss function in PyTorch? Loss Functions in PyTorch is here to help you.