danijar/fidjax
Frechet Inception Distance in JAX
This project helps machine learning engineers and researchers evaluate the quality of image generation models. It takes a set of generated images and a set of real reference images to produce a single Frechet Inception Distance (FID) score. This score indicates how similar the generated images are to the real ones, making it easier to compare and improve generative AI models.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer or researcher developing or comparing image generation models and need a reliable, high-performance metric for evaluating their output quality.
Not ideal if you are looking for a simple, out-of-the-box solution for image quality assessment without any programming, as it requires a developer to integrate it into their workflow.
Stars
7
Forks
—
Language
Python
License
—
Category
Last pushed
Jul 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/danijar/fidjax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
soran-ghaderi/torchebm
🍓 Build and train energy-based and diffusion models in PyTorch ⚡.
spqb/adabmDCApy
Pytorch implementation of adabmDCA
opendilab/GenerativeRL
Python library for solving reinforcement learning (RL) problems using generative models (e.g....
AstraZeneca/DiffAbXL
The official implementation of DiffAbXL benchmarked in the paper "Exploring Log-Likelihood...
G-U-N/UniRL
a unified reinforcement learning toolbox for joint RL on language models and diffusion models