1 repo
Tools for training and evaluating CycleGAN models on unpaired datasets.
Distinguishing note: Focuses on the training and evaluation workflow for CycleGAN.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · CycleGAN Training Utilities. Refine with filters or upvote what's useful.
This project is a deep learning framework designed for training and deploying image-to-image translation models. It serves as a research platform for experimenting with neural network architectures that transform visual content between distinct stylistic domains, supporting both paired and unpaired training data. The framework distinguishes itself through its support for cycle-consistency constraints, which allow for image translation between domains without requiring corresponding paired examples. It provides a structured pipeline that utilizes adversarial loss optimization, where generator
Supports training generative models on unpaired image collections and evaluating translation quality.