Celebrity Classifier
Model description
This model classifies a face to a celebrity. It is trained on tonyassi/celebrity-1000 dataset and fine-tuned on google/vit-base-patch16-224-in21k.
Dataset description
tonyassi/celebrity-1000 Top 1000 celebrities. 18,184 images. 256x256. Square cropped to face.
How to use
from transformers import pipeline
# Initialize image classification pipeline
pipe = pipeline("image-classification", model="tonyassi/celebrity-classifier")
# Perform classification
result = pipe('image.png')
# Print results
print(result)
Training and evaluation data
It achieves the following results on the evaluation set:
- Loss: 0.9089
- Accuracy: 0.7982
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0