IShengFang/SpectralNormalizationKeras

Spectral Normalization for Keras Dense and Convolution Layers

47
/ 100
Emerging

This project offers a simple way to improve the stability and performance of Keras-based Generative Adversarial Networks (GANs). It takes your existing Keras `Dense` and `Convolutional` layers and applies Spectral Normalization, resulting in higher-quality generated images and more robust training. This is ideal for machine learning researchers and practitioners working on deep learning models for image generation.

121 stars. No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher looking to enhance the stability and output quality of your Keras-based Generative Adversarial Networks, especially for image synthesis tasks.

Not ideal if you are working with machine learning models other than GANs or if your primary deep learning framework is not Keras.

deep-learning image-generation generative-adversarial-networks neural-network-training keras-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

121

Forks

34

Language

Jupyter Notebook

License

Last pushed

Dec 28, 2019

Commits (30d)

0

Get this data via API

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

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