README.md

metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: celebrity-classifier
    results: []

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