Publications by Gary Hutson

Graph Data Modeling with Python

30.06.2023

I am so excited to announce that I have a new book (in collaboration with Packt) that has just been launched, written with my co-author, the wonderful Matt Jackson.This books takes you from a nascent understanding of graph data science methods to a more confident user, all in under 250 pages.Matt and I have been working on this book for just under ...

3710 sym 2 img

Graph Data Modeling with Python

30.06.2023

I am so excited to announce that I have a new book (in collaboration with Packt) that has just been launched, written with my co-author, the wonderful Matt Jackson. This books takes you from a nascent understanding of graph data science methods to a more confident user, all in under 250 pages. Matt and I have been working on this book for just un...

3981 sym 2 img

Fine tune a Dreambooth model for image generation using Stable Diffusion with PyTorch

25.05.2023

I recently did a great talk at Leeds Data Science, where I presented how to fine tune a Stable Diffusion model, using Google’s Dreambooth method, to fine tune the model to create interesting image concepts for generation. This was well received (see: https://www.linkedin.com/posts/jumping-rivers-ltd_meetup-datascience-imagerecognition-activity-70...

15095 sym 28 img

Creating doodles with HED detection and ControlNet

29.03.2023

I previously did a blog post on the power of ControlNet and the various options you have at play when working with controlnet models.To reference the previous introduction to what are controlnets, please refer to my previous post on this: https://hutsons-hacks.info/using-controlnet-models-to-remodel-my-living-room.What is HED detection?Holistically...

8103 sym 22 img

Using ControlNet models to remodel my living room

09.03.2023

This post will use an old image of my house before I bought it, and remodelled the living room, to see how this model could be used to make suggestions on how it could be further remodelled. We will be using a suite of pre-trained ControlNet models, trained on hours of GPU time, to then fine tune these with a HuggingFace prompt.What is the ControlN...

11964 sym 14 img 1 tbl

Few Shot Learning with SetFit

24.02.2023

HuggingFace have been working on a model that can be used for small datasets. The aim is to leverage the pretrained transformer and use contrastive learning to augment and extend the dataset, by using similar labels that share a same dimensional space.In this tutorial I will talk you through what SetFit is and how to fine tune the model to provide ...

13753 sym 12 img

Stable Diffusion model for generating images of Fjords

05.01.2023

My family had the experience of going to the Norwegian Fjords in May 2022 and I took some great pictures on my new camera. Well now I have created a stable diffusion model that allows you to generate images of your own and get them to work with the Norweigen Fjord image set, this is located here: https://huggingface.co/datasets/StatsGary/dreamboo...

1797 sym 8 img

Stable Diffusion application with Streamlit

23.12.2022

This combines my love of Deep Learning and Transformer frameworks, with the ability to generate images from textual prompts.First of all I think I should explain a little of what is meant by stable diffusion, and this will be detailed in the next section. Then we will move on to building the stable diffusion class wrapper and we will use Streaml...

9920 sym 22 img

Connecting Python to SQL Server using trusted and login credentials

21.09.2020

The pypyodbc is the library you need to drive the connection to a SQL server database. If, like me, you struggle with connection strings, then please navigate to this site for help with all types of connection string: https://www.connectionstrings.com/.Installing with pip installTo install the relevant packages needed you will need to use pip ins...

2557 sym Python (669 sym/3 pcs) 2 img

Python Pandas Pro – Session One – Creation of Pandas objects and basic data frame operations

28.09.2020

I first started using Python a couple of years ago, when the limitations of some of the Deep Learning libraries in R became apparent.What I want to do is create a series of tutorials that allow you to get up to speed with Pandas for data frames in Python quickly.The first session will focus on the basics of Pandas and how to create your own panda...

3714 sym Python (3455 sym/17 pcs)