psellcam/LaplaceNet

A PyTorch Implementation of LaplaceNet:A Hybrid Energy-Neural Model for Deep Semi-Supervised Classification

30
/ 100
Emerging

This project offers a method for deep semi-supervised image classification. It helps machine learning practitioners classify large image datasets efficiently, even when only a small portion of the images are labeled. You provide your image data (like CIFAR-10/100 or Mini-ImageNet) with some labels, and it outputs a trained classification model capable of categorizing the unlabeled images.

No commits in the last 6 months.

Use this if you need to classify large image datasets and have a limited budget for manual data labeling, aiming to achieve high accuracy with fewer labeled examples.

Not ideal if your dataset is not image-based, or if you prefer a fully supervised learning approach with a completely labeled dataset.

image-classification semi-supervised-learning computer-vision deep-learning data-labeling-efficiency
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

15

Forks

6

Language

Shell

License

Last pushed

Feb 08, 2022

Commits (30d)

0

Get this data via API

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

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