Image-to-Image Translation with Conditional Adversarial Networks
Keras implementation of Pix2pix for image-to-image translation using conditional adversarial networks.
What is Image-to-Image Translation with Conditional Adversarial Networks?
pix2pix-keras is a Keras-based implementation of the Pix2pix model for image-to-image translation tasks. It uses conditional generative adversarial networks (cGANs) to transform images from one domain to another, such as converting sketches to photos or maps to satellite images. The project provides a complete training pipeline and utilities for working with datasets like facades.
Deep learning researchers, computer vision practitioners, and developers interested in generative models and image synthesis using Keras and TensorFlow.
It offers a straightforward, educational implementation of Pix2pix in Keras, making it easier to understand and experiment with conditional GANs compared to lower-level frameworks. The included dataset utilities and training scripts reduce setup time for image translation projects.
Overview
Image-to-Image Translation with Conditional Adversarial Networks (Pix2pix) implementation in keras
Use Cases
Best For
- Learning how conditional GANs work for image-to-image translation
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
