Michael Sugimura

Published in Towards Data Science

·Pinned

FGO StyleGAN: This Heroic Spirit Doesn’t Exist

When I first saw Nvidia’s StyleGAN’s results I felt like it looked like a bunch of black magic. I am not as experienced in the area of GANs as other parts of deep learning, this lack of experience and the thought that I really lacked the GPU firepower to train…

Machine Learning

11 min read

FGO StyleGAN: This Heroic Spirit Doesn’t Exist

Published in ShopRunner

·Mar 19, 2021

A Tricksy Look at Outfitting: Kitsune

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…

Data Science

15 min read

Published in Towards Data Science

·May 11, 2020

Project Pendragon + Tonks: Multi-Task Feature Extraction for Farming Fate Grand Order

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…

Data Science

13 min read

Project Pendragon + Tonks: Multi-Task Feature Extraction for Farming Fate Grand Order

Published in ShopRunner

·Apr 28, 2020

Tonks: Building One (Multi-Task) Model to Rule Them All!

Co-written by Nicole Carlson and Michael Sugimura — 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…

Deep Learning

9 min read

Tonks: Building One (Multi-Task) Model to Rule Them All!

Published in Towards Data Science

·Feb 25, 2020

Breaking the Game: Pendragon Four Rise of Merlin

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…

Reinforcement Learning

16 min read

Breaking the Game: Pendragon Four Rise of Merlin

Published in Towards Data Science

·Feb 17, 2020

Pendragon Four: Training Pipeline Deeper Dive for Multi Agent Reinforcement Learning

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…

Deep Lear

14 min read

Pendragon Four: Training Pipeline Deeper Dive for Multi Agent Reinforcement Learning

Published in Towards Data Science

·Dec 17, 2019

Pendragon Four: Multi-Agent Reinforcement Learning with Fate Grand Order

Multi-agent reinforcement learning in a custom game environment to train 4 agents and have them play the mobile phone game Fate Grand Order —

Machine Learning

21 min read

Pendragon Four: Multi-Agent Reinforcement Learning with Fate Grand Order

Published in Towards Data Science

·Oct 9, 2019

This Dress Doesn’t Exist

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…

Machine Learning

12 min read

Published in Towards Data Science

·Sep 9, 2019

Building and Labeling Image Datasets for Data Science Projects

Some tips and tricks for building image datasets — 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. …

Machine Learning

7 min read

Building and Labeling Image Datasets for Data Science Projects

Published in Towards Data Science

·Jun 10, 2019

BERT Classifier: Just Another Pytorch Model

At the end of 2018 Google released BERT and it is essentially a 12 layer network which was trained on all of Wikipedia. The training protocol is interesting because unlike other recent language models BERT is trained in to take into account language context from both directions rather than just…

Machine Learning

9 min read

BERT Classifier: Just Another Pytorch Model