PyTorch Autograd and Training Models

Recently I’ve found myself wanting to dig a bit deeper into PyTorch to really understand how it works and hopefully figure out how to expand on my skillset to try new things. To aid this, I’ve been following the Deep Learning with PyTorch book by Eli Stevens, Luca Antiga and Thomas Viehmann. The book itself has been great and highly useful. I recommend it to anyone. In my observations, one the hardest things for newer users of PyTorch to understand is how to train a model....

February 1, 2021 · 6 min · James Malcolm

Deploying Machine Learning Models with Docker

There are a lot of articles out there explaining how to wrap Flask around your machine learning models to serve them as a RESTful API. This article assumes that you already have wrapped your model in a Flask REST API, and focuses more on getting it production ready using Docker. Motivation Why do we need to further work on our Flask API to make it deployable? Flask’s built-in server is not suitable for production Docker allows for smoother deployments, more reliability, and better developer-production parity than attempting to run Flask on a standard Virtual Machine....

February 24, 2020 · 6 min · James Malcolm