Skip to content
forked from created-Bi/VQA-GPT

Offer the benchmark and tools to evaluate AI-generated visual concepts including images, audios, 3d and videos.

Notifications You must be signed in to change notification settings

tivonwu/VQA-GPT

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

VQA-GPT

Offer the benchmark and tools to evaluate AI-generated visual concepts including images, audios, 3d and videos.

Benchmark

1. FFHQ-Attr(Face)

This benchmark contains 13061 Asian facical images with 8 attributes: age, gender, hair, facial feature, angle of view, skin color, face block, and facial expression. Demo of the image

Why we need this benchmark?

Answer: A fine-grained and targeted benchmark to illustrate the effectiveness of the generative model which can yield stylish individual pictures. Auto-Pipeline of AI-generated image evaluation

Acknowledgements

1、Our FFHQ-Attr-benchmark is developed based on the FFHQ-benchmark, thus thanks to https://github.com/NVlabs/ffhq-dataset.git.

About

Offer the benchmark and tools to evaluate AI-generated visual concepts including images, audios, 3d and videos.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published