# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("michaelgathara/vit-face-universal")
model = AutoModelForImageClassification.from_pretrained("michaelgathara/vit-face-universal")Quick Links
ViT Face Expression (Universal / Combined)
This model is a fine-tuned version of trpakov/vit-face-expression on a massive combined dataset including:
- Zenodo (IFEED)
- Mendeley (GFFD-2025)
- RAF-DB
- AffectNet
Model Description
- Architecture: Vision Transformer (ViT)
- Task: Facial Emotion Recognition
- Emotions: Anger, Disgust, Fear, Happiness, Neutral, Sadness, Surprise
- Goal: General-purpose robustness across varied domains (web images, lab settings, etc.)
Usage
from transformers import ViTImageProcessor, ViTForImageClassification
from PIL import Image
import requests
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
repo_name = "michaelgathara/vit-face-universal"
processor = ViTImageProcessor.from_pretrained(repo_name)
model = ViTForImageClassification.from_pretrained(repo_name)
inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 7 emotions
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
- Downloads last month
- 1
Model tree for michaelgathara/vit-face-universal
Base model
trpakov/vit-face-expression
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="michaelgathara/vit-face-universal") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")