shaohua0116/DCGAN-Tensorflow

A Tensorflow implementation of Deep Convolutional Generative Adversarial Networks trained on Fashion-MNIST, CIFAR-10, etc.

45
/ 100
Emerging

This project helps machine learning practitioners generate new, realistic images from existing datasets. You provide a collection of images (like fashion items or handwritten digits), and the system learns to produce entirely new images that resemble the originals. This is useful for researchers and developers working on computer vision tasks who need synthetic data.

No commits in the last 6 months.

Use this if you need to generate artificial images that mimic the characteristics of a training dataset, for tasks like data augmentation or exploring generative models.

Not ideal if you need an out-of-the-box solution for complex image editing or high-resolution photorealistic image generation without deep learning expertise.

image-generation synthetic-data computer-vision-research deep-learning-experimentation adversarial-networks
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

71

Forks

29

Language

Python

License

MIT

Last pushed

Dec 10, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/shaohua0116/DCGAN-Tensorflow"

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