Some preliminary takeaways — This is not a judgement piece. I am merely showing a few mathematical perspectives and unpacking a few formulas. Vaccine allocation is going to be a difficult problem to solve in the coming years(!). …

Continuing on, but now to the ‘big kahuna’ — Now we have to tackle the meat of the entire project and everything that came before this was set up to allow for training to happen seamlessly — downloading the dataset, formatting everything for entry into the network, using creating data transforms for image manipulation and creating dataloaders that help…

Upload your image and convince yourself it works using Google Colab — It’s Monday morning and I’m channeling my inner Jeremy Howard (again). Over the last few months, I have seen plenty of facial recognition guides and some of them are really quite good. The problem is, each student of deep learning or machine vision becomes interested through different venues. …

Compare brute force to image integral using Google Colab — In my quest to learn more about computer vision and python, I’ve been reading about the Viola-James object detection frame work, best summarized by the paper here. In it, they describe the concept of an image integral, a sort of summed area table for an array describing an image, with…

Getting the dataset ready for training — A quick recap of what we’ve done so far: Part 1 — Overview of the entire project. No python was required, only a Google and Kaggle account. Hopefully you have convinced yourself that you personally are able to run the code in its entirety, as well as testing it. Part…

CPU, GPU, Dataset Setup — I hope you all had a chance to preview Part 1 of this series which did not require any knowledge of python, just a Google and Kaggle account (the latter only to authenticate yourself so you can download the dataset.) As a quick overview, we were able to train the…

Train a deep neural network with only a few clicks — The code example I’m providing in this piece is a result of hours of frustration and sleuthing around on the internet. When I first started teaching myself about deep neural networks, I wanted to find something I could readily download, plug and play and run — and this was hard…

Porting a well known problem into the latest cloud computing service — Google’s Colab is a powerful tool, just as many of you have gotten used to Google Drive, Docs, Sheets. You’re able to run python code on a remote machine and even have access to GPU / TPUs. Recently I became very interested in Brian Christian and Tom Griffiths book ‘Algorithms…

I’ve taken to Jeremy Howard’s advice to start blogging and that your learnings may help the ‘person right behind you’ in learning Python / PyTorch / what have you. Although I find the fastai book a little difficult to follow — apparently there are some problems using this in a…