joisino/speedbook

書籍『深層ニューラルネットワークの高速化』のサポートサイトです。

31
/ 100
Emerging

This provides practical code examples and notebooks for optimizing deep neural networks. It demonstrates various techniques to make your AI models run faster and more efficiently. You provide a deep learning model, and these notebooks guide you through steps to improve its speed and reduce resource consumption. It's intended for AI engineers, data scientists, and machine learning practitioners who build and deploy deep learning solutions.

No commits in the last 6 months.

Use this if you need to accelerate the performance of your deep neural networks for faster training, inference, or to reduce computational costs.

Not ideal if you are looking for a pre-built, out-of-the-box solution for general AI model development without focusing on optimization.

deep-learning-optimization AI-model-acceleration neural-network-efficiency machine-learning-engineering GPU-optimization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

61

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/joisino/speedbook"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.