dima806's picture
Update README.md
db3bbe4 verified
|
raw
history blame
1.17 kB
metadata
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 54% 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     0.0000    0.0000    0.0000       180
         3-9     0.6799    0.8623    0.7603      1249
       10-19     0.4928    0.2201    0.3043      1086
       20-29     0.5780    0.7852    0.6658      3026
       30-39     0.4461    0.4202    0.4328      2099
       40-49     0.4589    0.3740    0.4121      1238
       50-59     0.4213    0.4800    0.4487       725
       60-69     0.0000    0.0000    0.0000       286
more than 70     0.0000    0.0000    0.0000       111

    accuracy                         0.5385     10000
   macro avg     0.3419    0.3491    0.3360     10000
weighted avg     0.4943    0.5385    0.5039     10000