---
license: apache-2.0
metrics:
- accuracy
- f1
base_model:
- google/vit-base-patch16-224-in21k
pipeline_tag: image-classification
library_name: transformers
---
Detects age group with about 18% accuracy based on an image.

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

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6449300e3adf50d864095b90/sG1GZFgo5TlzzFqal5obl.png)

```
Classification report:

              precision    recall  f1-score   support

         0-2     0.0000    0.0000    0.0000         0
         3-9     0.1667    0.2500    0.2000         8
       10-19     0.1667    0.0769    0.1053        13
       20-29     0.4000    0.3243    0.3582        37
       30-39     0.0000    0.0000    0.0000        18
       40-49     0.0000    0.0000    0.0000        13
       50-59     0.1579    0.5000    0.2400         6
       60-69     0.0000    0.0000    0.0000         3
more than 70     0.0000    0.0000    0.0000         2

    accuracy                         0.1800       100
   macro avg     0.0990    0.1279    0.1004       100
weighted avg     0.1925    0.1800    0.1766       100
```