liujie-zheng/face-to-bmi-vit

Predict the Body Mass Index with one image of a human face, with state-of-the-art results.

39
/ 100
Emerging

Based on the Vision Transformer (ViT) architecture indicated by the project name, this model leverages transformer-based feature extraction from facial images to regress continuous BMI values, achieving MAE of 3.02 on augmented datasets. The implementation includes data augmentation strategies and conda-based training pipelines supporting both original and augmented datasets. Inference is exposed via command-line demo scripts designed for single-image predictions with minimal preprocessing requirements.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

35

Forks

7

Language

Python

License

MIT

Last pushed

Jan 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/liujie-zheng/face-to-bmi-vit"

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