This blog is based on a hack week I did near the end of 2020. For background, the ShopRunner Data Science allows members to spend a week per quarter working on a ShopRunner-related topic of their choice.

Ever since getting involved in e-commerce data science, one of the things I have been thinking about has been automating outfit creation. Starting to work at ShopRunner, my general focus has been helping the team build out more deep learning and, in particular, computer vision expertise. For the first year and a half or so, the focus was on building out those foundational…

When not blogging about data science, I work as a Senior Data Scientist at an e-commerce company called ShopRunner. Over the past year, our team has been building out large multi-task deep learning ensembles to predict relevant fashion attributes and characteristics of products within our product catalog using both images and text. Recently, our team open-sourced the main training pipelines and framework that we have been building internally to train our multi-task learners in a package called Tonks. Tonks is available to install on pypi, with the source code available on GitHub here.

As we went through the process of…

NOTE: Our team previously had a tradition of naming projects with terms or characters from the Harry Potter series, but we are disappointed by J.K. Rowling’s persistent transphobic comments. In response, we renamed the Tonks Library as Octopod. More details on that process here.

Intro

Nicole Carlson and Michael Sugimura are the lead developers on Tonks, a multi-task deep learning library (pypi, github). This post is the story of how we built this library together. We will discuss technical details of the library as well as interpersonal challenges we faced along the way. …

In my first Pendragon Four blog I introduced my multi-agent reinforcement learning (RL) setup for the mobile phone game Fate Grand Order (FGO) I listed a few goals:

1) Add supports to the game

FGO does not have a player vs player aspect and basically all the characters are viable for use, but it still has a reasonably defined meta. In gaming, the meta roughly describes strategies, characters, or weapons that are more dominant than others. In FGO the meta is defined largely by the support characters that are available which enable powerful/dominant strategies. …

Over the past year I have made various versions of neural network powered bots to play the game Fate Grand Order (FGO), loosely called Project Pendragon. The work around Project Pendragon ranges from feature extraction with a series of neural networks to get information about the current game state to my most recent additions three neural networks to control each of the three characters active on the game screen. These three and one additional bot for picking action cards are the four reinforcement learning (RL) agents that make up my current version of the project, Pendragon Four.

My recent post…

This post was originally published on the Shoprunner Engineering blog here feel free to check it out and at some of the other work our teams are doing.

This Dress Doesn’t Exist

Our ShopRunner Data Science team allows all members to have a quarterly hack week. It is important for data science teams to keep innovating so once per quarter team members are allowed to spend a week working on more speculative projects of their choice. For my 2019 Q3 hack week I decided to build a series of generator models to attempt to create fake products. Generator models are models commonly trained to…

Using standardized datasets is great for benchmarking new models/pipelines or for competitions. But for me at least a lot of fun of data science comes when you get to apply things to a project of your own choosing. One of the key parts of this process is building a dataset.

So there are a lot of ways to build image datasets. For certain things I have legitimately just taken screenshots like when I was sick and built a facial recognition dataset using season 4 of the Flash and annotated it with labelimg. …