
hlb-CIFAR10
by tysam-code (personal account)
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!) (description from the project’s GitHub page)
Repository facts
- Stars
- 1,316
- Forks
- 81
- Open issues and pull requests
- 3
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- tysam-code · Personal account
- Created
- Dec 11, 2022
- Last push
- Dec 18, 2024
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 7,714: HunterMcGushion/hyperparameter_hunter
Easy hyperparameter optimization and automatic result saving across machine learning algorithms and libraries
704 starsPythonMITLast push Jan 20, 2021
Rank 5,270: Hyperparticle/one-pixel-attack-keras
Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet
1,240 starsJupyter NotebookMITLast push Apr 24, 2024
Rank 3,199: uptrain-ai/uptrain
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding u…
2,366 starsPythonApache-2.0Last push Aug 18, 2024
Rank 37: pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
104,842 starsPythonOther licenseLast push Oct 18, 2026
Rank 216: explosion/spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
33,968 starsPythonMITLast push Oct 12, 2026
Rank 382: onnx/onnx
Open standard for machine learning interoperability
21,597 starsPythonApache-2.0Last push Oct 18, 2026