liujie-zheng/face-to-bmi-vit
Predict the Body Mass Index with one image of a human face, with state-of-the-art results.
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.
Stars
35
Forks
7
Language
Python
License
MIT
Category
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.
Related frameworks
lovnishverma/health-category-predict
A simple Flask web app that predicts health status based on BMI data using a Random Forest Classifier.
sandudul/BMI-Category-Predictor
This full-stack app leverages: Python libraries: scikit-learn, pandas, numpy, joblib, and Flask...
raquelrguezs/advanced-health-analytics
Clinical data analytics pipeline for hospital readmission risk prediction using synthetic EHR data.
analyst-ted/hospital-readmission-prediction
ML model to predict 30-day hospital readmission using patient data
global-ad-snap/diabetic-readmission-survival-analysis
Survival analysis of diabetic patient readmission using Cox Proportional Hazards and Random...