Home

Awesome

GAN_Metrics-Tensorflow

Simple Tensorflow implementation of metrics for GAN evaluation

<div align="center"> <img src="./assets/description.png"> </div>

Summary

NameDescriptionPerformance score
Inception scoreKL-Divergence between conditional and marginal label distributions over generated data.Higher is better.
Frechet-Inception distanceWasserstein-2 distance between multi-variate Gaussians fitted to data embedded into a feature space.Lower is better.
Kernel-Inception distanceMeasures the dissimilarity between two probability distributions Pr and Pg using samples drawn independently from each distribution.Lower is better.

Usage

├── real_source 
    ├── aaa.png
    ├── bbb.jpg
├── real_target 
    ├── ccc.png
    ├── ddd.jpg
├── fake 
    ├── ccc_fake.png
    ├── ddd_fake.jpg
├── main.py
├── inception_score.py
└── frechet_kernel_Inception_distance.py
> python main.py

Reference

Author

Junho Kim