Formula Slug Autonomous Onboarding Project

Description

This project takes the KMNIST dataset, which consists of images of 10 different Japanese characters, and uses a Pytorch NN to identify characters in the test set.

Setup

# Create environment
conda env create -f environment.yml

# Activate environment
conda activate pytorch_env

Usage

jupyter notebook Autonomous_Homework.ipynb

Data

The Kuzushiji-MNIST dataset is a drop-in replacement of the MNIST dataset, which consists of 70000 28x28 grayscale images of Japanese Hiragana characters.