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!)
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.
Stars
1,300
Forks
80
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
raghakot/keras-resnet
Residual networks implementation using Keras-1.0 functional API
titu1994/DenseNet
DenseNet implementation in Keras
liuzhuang13/DenseNet
Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).
BIGBALLON/cifar-10-cnn
Play deep learning with CIFAR datasets
bamos/densenet.pytorch
A PyTorch implementation of DenseNet.