Lots of evaluation metrics of Generative Adversarial Networks in pytorch
Work In Progress...
Clone
the repository and Move
the directory.$ git clone https://github.com/kozistr/gan-metrics
$ cd ./gan-metrics
Install
the requirements.txt
$ pip3 install -r requirements.txt
Configure
the config.yml
open the file and edit
Run
$ python3 -m metrics
Metric | Paper | Code |
---|---|---|
Inception Score (IS) | arXiv | code |
Frechet Inception Distance (FID) | code | |
Kernel Inception Distance (KID) | ||
SSIM & PSNR | ||
Precision & Recall | ||
Earth Mover's Distance (EMD, a.k.a wasserstein distance) | wiki | code |
Perceptual Path Length (PPL) | ||
Learned Perceptual Image Patch Similarity (LPIPS) | arXiv | |
Reliable Fidelity & Diversity (PRDC) | arXiv | |
Amazon's Mechanical Turk (AMT) | Amazon |
You can edit the transform
function with your flavor!
Hyeongchan Kim / @kozistr