sfuneno/emotion-vit-base

Tuned Vision Transformer (ViT-Base)

Overview

This repository contains a fine-tuned Google Vision Transformer (ViT-Base) model for image classification.
The model is based on google/vit-base-patch16-224 and has been tuned on a task-specific dataset to make it perform well in emotion classification.

---

Model Details

• Base model: google/vit-base-patch16-224
• Architecture: Vision Transformer (ViT)
• Patch size: 16 × 16
• Input resolution: 224 × 224
• Framework: PyTorch + Hugging Face Transformers
• Fine-tuning: Supervised fine-tuning on labeled RAF-DB dataset

---

Usage

Load the model

from transformers import AutoImageProcessor, AutoModelForImageClassification

processor = AutoImageProcessor.from_pretrained(
    "sfuneno/google-vit-base"
)
model = AutoModelForImageClassification.from_pretrained(
    "sfuneno/google-vit-base"
)