tysam-code/hlb-CIFAR10
A PyTorch implementation achieving near-world-record single-GPU CIFAR-10 training speed using optimized CNN architectures.
Not currently ranked — collecting fresh signals.
star history
This repository implements a highly optimized convolutional neural network for CIFAR-10 image classification, originally inspired by David Page’s work but rewritten for rapid experimentation. It focuses on maximizing training speed on a single GPU through architectural tweaks, hyperparameter tuning, memory format optimizations, and Dirac initialization. The project holds or held the world record for single-GPU CIFAR-10 training time on an A100, demonstrating state-of-the-art training throughput for computer vision models.
Frequently asked
- What is tysam-code/hlb-CIFAR10?
- A PyTorch implementation achieving near-world-record single-GPU CIFAR-10 training speed using optimized CNN architectures.
- Is hlb-CIFAR10 open source?
- Yes — tysam-code/hlb-CIFAR10 is open source, released under the Apache-2.0 license.
- What language is hlb-CIFAR10 written in?
- tysam-code/hlb-CIFAR10 is primarily written in Python.
- How popular is hlb-CIFAR10?
- tysam-code/hlb-CIFAR10 has 1.3k stars on GitHub.
- Where can I find hlb-CIFAR10?
- tysam-code/hlb-CIFAR10 is on GitHub at https://github.com/tysam-code/hlb-CIFAR10.