Image Classification
Transformers
Safetensors
English
age-estimation
age-prediction
gender-classification
race-classification
ethnicity-classification
face-analysis
demographics
facial-attributes
fairness
bias-evaluation
convnext
Instructions to use TimmaJ/age-gender-race-prediction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TimmaJ/age-gender-race-prediction with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="TimmaJ/age-gender-race-prediction") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TimmaJ/age-gender-race-prediction", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| model,metric,n,estimate,lo,hi | |
| ConvNext(yours),gender accuracy,2000,0.9625,0.954,0.9705 | |
| ConvNext(yours),race accuracy,2000,0.807,0.79,0.8245 | |
| ConvNext(yours),age MAE,2000,4.998,4.809,5.194 | |
| MiVOLO,gender accuracy,1995,0.9719,0.9644,0.9794 | |
| MiVOLO,age MAE,1995,5.637,5.429,5.841 | |
| FairFace,gender accuracy,2000,0.9115,0.8985,0.924 | |
| FairFace,race accuracy,2000,0.598,0.576,0.62 | |
| FairFace,age MAE,2000,7.545,7.278,7.836 | |
| DeepFace,gender accuracy,2000,0.8885,0.8745,0.902 | |
| DeepFace,race accuracy,2000,0.664,0.6435,0.685 | |
| DeepFace,age MAE,2000,6.418,6.145,6.683 | |
| CLIP,gender accuracy,2000,0.9715,0.964,0.9785 | |
| CLIP,race accuracy,2000,0.5565,0.5355,0.578 | |
| CLIP,age MAE,2000,9.363,9.0,9.707 | |
| InsightFace,gender accuracy,1959,0.9117,0.8984,0.9245 | |
| InsightFace,age MAE,1959,7.23,6.917,7.569 | |