tysam-code/hlb-CIFAR10

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

42
/ 100
Emerging

This project helps machine learning researchers quickly test new ideas for image classification models. It takes the CIFAR-10 dataset as input and rapidly trains a convolutional neural network, outputting a highly accurate model in record time on a single GPU. It's designed for researchers experimenting with new architectures or training techniques for computer vision.

1,300 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or student who wants to rapidly prototype and test new neural network ideas for image classification.

Not ideal if you need a production-ready, long-term stable codebase or are working with datasets other than CIFAR-10 without significant modifications.

deep-learning image-classification computer-vision ml-research neural-network-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

1,300

Forks

80

Language

Python

License

Apache-2.0

Last pushed

Dec 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tysam-code/hlb-CIFAR10"

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