MetaCLIP-2-Gender-Identifier

MetaCLIP-2-Gender-Identifier is an image classification vision-language encoder model fine-tuned from facebook/metaclip-2-worldwide-s16 for a single-label classification task. It is designed to predict the gender of a person from an image using the MetaClip2ForImageClassification architecture.

MetaCLIP 2: A Worldwide Scaling Recipe : https://huggingface.co/papers/2507.22062

Classification Report:
              precision    recall  f1-score   support

      female     0.9815    0.9631    0.9722      1600
        male     0.9638    0.9819    0.9728      1600

    accuracy                         0.9725      3200
   macro avg     0.9727    0.9725    0.9725      3200
weighted avg     0.9727    0.9725    0.9725      3200

---

The model categorizes images into two gender classes:

• Class 0: "female"
• Class 1: "male"

Run with Transformers

!pip install -q transformers torch pillow gradio

import gradio as gr
import torch
from transformers import AutoImageProcessor, AutoModelForImageClassification
from PIL import Image

# Model name from Hugging Face Hub
model_name = "prithivMLmods/MetaCLIP-2-Gender-Identifier"

# Load processor and model
processor = AutoImageProcessor.from_pretrained(model_name)
model = AutoModelForImageClassification.from_pretrained(model_name)
model.eval()

# Define labels
LABELS = {
    0: "female",
    1: "male"
}

def age_classification(image):
    """Predict the age group of a person from an image."""
    image = Image.fromarray(image).convert("RGB")
    inputs = processor(images=image, return_tensors="pt")

    with torch.no_grad():
        outputs = model(**inputs)
        logits = outputs.logits
        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()

    predictions = {LABELS[i]: round(probs[i], 3) for i in range(len(probs))}
    return predictions

# Build Gradio interface
iface = gr.Interface(
    fn=age_classification,
    inputs=gr.Image(type="numpy", label="Upload Image"),
    outputs=gr.Label(label="Predicted Gender"),
    title="MetaCLIP-2-Gender-Identifier",
    description="Upload an image to predict the person's gender."
)

# Launch app
if __name__ == "__main__":
    iface.launch()

Sample Inference:

Intended Use:

The MetaCLIP-2-Gender-Identifier model is designed to classify images into gender categories. Potential use cases include:

• Demographic Analysis: Supporting research and business insights into gender-based distribution.
• Health and Fitness Applications: Assisting in gender-specific analytics and recommendations.
• Security and Access Control: Supporting gender-based identity verification systems.
• Retail and Marketing: Enabling improved personalization and customer segmentation.
• Forensics and Surveillance: Assisting in identity estimation for investigative purposes.