Posts

  • Looking Back @ Ráiteas

    It’s been 7 years since the end of my first startup - a startup which failed. Looking back I wonder about the learnings - what would I tell myself, and what would I tell new founders?

  • Training tiny models efficiently with Fast AI v2 and Pytorch

    Everyone talks mostly about the next 1 billion+ parameter model, but I have lots of small, even tiny, models which still takes a while to train due to large data volumes and inefficient use of the GPU.

  • Fast AI 2 transformations

    Data loading is at the heart of any machine learning project and with Fast AI 2 this has become easier and more transparent. In this post I’ll look at the data transforms, as well as how to get some insights into what is happening where and when, during the data loading and data transformation steps.

subscribe via RSS