dima806's picture
Update README.md
25e0864 verified
|
raw
history blame
1.2 kB
metadata
license: apache-2.0
metrics:
  - accuracy
  - f1
base_model:
  - google/vit-base-patch16-224-in21k
pipeline_tag: image-classification
library_name: transformers
datasets:
  - nateraw/fairface

Detects age group with about 58% accuracy based on an image.

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

image/png

Classification report:

              precision    recall  f1-score   support

         0-2     0.8345    0.6444    0.7273       180
         3-9     0.7698    0.8327    0.8000      1249
       10-19     0.5395    0.3462    0.4218      1086
       20-29     0.6201    0.7548    0.6809      3026
       30-39     0.4790    0.4774    0.4782      2099
       40-49     0.4826    0.4031    0.4393      1238
       50-59     0.4899    0.5021    0.4959       725
       60-69     0.4215    0.3846    0.4022       286
more than 70     0.0000    0.0000    0.0000       111

    accuracy                         0.5791     10000
   macro avg     0.5152    0.4828    0.4939     10000
weighted avg     0.5653    0.5791    0.5671     10000