DingKe/nn_playground

Experimental keras implementation of novel neural network structures

51
/ 100
Established

This is a collection of experimental neural network implementations, primarily focusing on novel architectures and techniques like Binary, XNOR, and Ternary Networks, as well as various GANs (WGAN, LSGAN, GLSGAN) and normalization methods. It allows machine learning researchers and practitioners to explore and evaluate cutting-edge models for tasks like image generation or efficient model deployment. You provide data (e.g., images for GANs, general datasets for classification) and it outputs trained models using these specialized architectures.

432 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or advanced practitioner interested in experimenting with non-standard neural network architectures for efficiency or specific performance characteristics.

Not ideal if you are looking for ready-to-use, production-grade models or a beginner's introduction to standard neural networks.

deep-learning-research neural-network-design model-optimization generative-models experimental-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

432

Forks

148

Language

Python

License

MIT

Last pushed

Sep 29, 2018

Commits (30d)

0

Get this data via API

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

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