Michael Sugimura – Medium

Michael Sugimura

Pinned

Michael Sugimura
in
Towards Data Science

FGO StyleGAN: This Heroic Spirit Doesn’t Exist

Finetuning Nvidia’s StyleGAN to a custom Fate Grand Order use case

May 20, 2019

FGO StyleGAN: This Heroic Spirit Doesn’t Exist

May 20, 2019

Michael Sugimura

A Tricksy Look at Outfitting: Kitsune

An approach to outfitting using attribute vector representations and a multi-task generator model to create outfits for a given seed item

Mar 19, 2021

A Tricksy Look at Outfitting: Kitsune

Mar 19, 2021

Michael Sugimura
in
Towards Data Science

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

Using a Tonks trained multi-task pytorch model to extract features from the mobile phone game Fate Grand Order

May 11, 2020

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

May 11, 2020

Michael Sugimura

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

a new library for training multi-task networks in pytorch with images and or text.

Apr 28, 2020

Hexagonal icon that says Tonks and has five different hairstyles pictured all in neon colors.

Apr 28, 2020

Michael Sugimura
in
Towards Data Science

Breaking the Game: Pendragon Four Rise of Merlin

Multi-agent reinforcement learning for the mobile phone game Fate Grand Order adding in powerful supports to clear late-game content

Feb 25, 2020

Breaking the Game: Pendragon Four Rise of Merlin

Feb 25, 2020

Michael Sugimura
in
Towards Data Science

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

Deeper dive into training multiple RL agents simultaneously to play the mobile phone game Fate Grand Order

Feb 17, 2020

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

Feb 17, 2020

Michael Sugimura
in
Towards Data Science

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

Dec 17, 2019

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

Dec 17, 2019

Michael Sugimura
in
Towards Data Science

This Dress Doesn’t Exist

Fine tuning GPT-2 and StyleGAN for a fashion use case to generate synthetic product images and descriptions

Oct 9, 2019

This Dress Doesn’t Exist

Oct 9, 2019

Michael Sugimura
in
Towards Data Science

Building and Labeling Image Datasets for Data Science Projects

Some tips and tricks for building image datasets

Sep 9, 2019

Building and Labeling Image Datasets for Data Science Projects

Sep 9, 2019

Michael Sugimura
in
Towards Data Science

BERT Classifier: Just Another Pytorch Model

Building a custom Pytorch pipeline for a BERT classifier to figure out how BERT works piece by piece

Jun 10, 2019

BERT Classifier: Just Another Pytorch Model

Jun 10, 2019

Michael Sugimura

Michael Sugimura

data scientist, gamer, martial artist, photographer, and chef… also part time house cat. https://www.linkedin.com/in/michael-sugimura-b8120940/

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams