Skip to content
Classification of Simpsons characters using fast.ai
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
imgs
.gitignore
Pipfile
README.md
requirements.txt
train.py

README.md

Simpsons classification

Classification of Simpsons characters

Introduction

This is a simple demo for classifying Simpsons characters with fast.ai and optimizing the neural network by monitoring and comparing runs with Weights & Biases.

Hyper-parameters are defined pseudo-randomly and every run is automatically logged onto Weighs & Biases for easier analysis/interpretation of results and how to optimize the architecture.

Usage

  1. Install dependencies through requirements.txt, Pipfile or manually (Pytorch, Fast.ai & Wandb)

  2. Log in or sign up for an account -> wandb login

  3. Run python train.py

  4. Visualize and compare your runs through generated link

    alt text

Results

After running the script a few times, you will be able to compare quickly a large combination of hyperparameters. As an example, you can refer to my runs.

alt text

Feel free to modify the script and define your own hyperparameters.

You can’t perform that action at this time.