mseitzer/pytorch-fid

Compute FID scores with PyTorch.

57
/ 100
Established

This tool helps researchers and practitioners evaluate the quality of images generated by AI models, particularly Generative Adversarial Networks (GANs). It takes two sets of images—one real and one generated—and outputs a Fréchet Inception Distance (FID) score, which indicates how similar the generated images are to the real ones. This is primarily for machine learning researchers and engineers developing or benchmarking image generation models.

3,833 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are a machine learning researcher or engineer working with PyTorch and need to objectively quantify the visual quality of images produced by your generative models against real image datasets.

Not ideal if you need exact, cross-paper comparable FID scores, as slight differences in implementation might lead to minor discrepancies compared to the original TensorFlow version.

generative-ai image-synthesis model-evaluation computer-vision deep-learning-research
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

3,833

Forks

529

Language

Python

License

Apache-2.0

Last pushed

Jul 03, 2024

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mseitzer/pytorch-fid"

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