---
license: apache-2.0
datasets:
- nateraw/fairface
metrics:
- accuracy
- f1
base_model:
- google/vit-base-patch16-224-in21k
pipeline_tag: image-classification
---
Detects gender with about 88% accuracy based on an image.

See https://www.kaggle.com/code/dima806/gender-image-classification-vit for details.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6449300e3adf50d864095b90/NLKajM7gBl16afwtMGLpD.png)

```
Classification report:

              precision    recall  f1-score   support

      Female     0.8563    0.8938    0.8746       480
        Male     0.8978    0.8615    0.8793       520

    accuracy                         0.8770      1000
   macro avg     0.8770    0.8776    0.8770      1000
weighted avg     0.8779    0.8770    0.8770      1000
```