Update README.md

README.md

@@ -2,8 +2,28 @@
 license: apache-2.0
 datasets:
 - prithivMLmods/Face-Age-10K
+language:
+- en
+base_model:
+- google/siglip2-base-patch16-512
+pipeline_tag: image-classification
+library_name: transformers
+tags:
+- age-detection
+- SigLIP2
+- biology
 ---
 
+![467.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/LA6do4hgVi-zNarLEhVGR.png)
+
+# facial-age-detection
+
+> facial-age-detection is a vision-language encoder model fine-tuned from `google/siglip2-base-patch16-512` for **multi-class image classification**. It is trained to detect and classify human faces into **age groups** ranging from early childhood to elderly adults. The model uses the `SiglipForImageClassification` architecture.
+
+> \[!note]
+> SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
+> [https://arxiv.org/pdf/2502.14786](https://arxiv.org/pdf/2502.14786)
+
 ```py
 Classification Report:
               precision    recall  f1-score   support
@@ -23,3 +43,93 @@ weighted avg     0.8226    0.8225    0.8223      9165
 ```
 
 ![download (1).png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/E_8ykSA-ZqEK0_Jtch5dD.png)
+
+---
+
+## Label Space: 8 Classes
+
+```
+Class 0: age 01-10  
+Class 1: age 11-20  
+Class 2: age 21-30  
+Class 3: age 31-40  
+Class 4: age 41-55  
+Class 5: age 56-65  
+Class 6: age 66-80  
+Class 7: age 80 +
+```
+
+---
+
+## Install Dependencies
+
+```bash
+pip install -q transformers torch pillow gradio hf_xet
+```
+
+---
+
+## Inference Code
+
+```python
+import gradio as gr
+from transformers import AutoImageProcessor, SiglipForImageClassification
+from PIL import Image
+import torch
+
+# Load model and processor
+model_name = "prithivMLmods/facial-age-detection"  # Update with actual model name on Hugging Face
+model = SiglipForImageClassification.from_pretrained(model_name)
+processor = AutoImageProcessor.from_pretrained(model_name)
+
+# Updated label mapping
+id2label = {
+    "0": "age 01-10",
+    "1": "age 11-20",
+    "2": "age 21-30",
+    "3": "age 31-40",
+    "4": "age 41-55",
+    "5": "age 56-65",
+    "6": "age 66-80",
+    "7": "age 80 +"
+}
+
+def classify_image(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()
+
+    prediction = {
+        id2label[str(i)]: round(probs[i], 3) for i in range(len(probs))
+    }
+
+    return prediction
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=classify_image,
+    inputs=gr.Image(type="numpy"),
+    outputs=gr.Label(num_top_classes=8, label="Age Group Classification"),
+    title="Facial Age Detection",
+    description="Upload a face image to estimate the age group: 01–10, 11–20, 21–30, 31–40, 41–55, 56–65, 66–80, or 80+."
+)
+
+if __name__ == "__main__":
+    iface.launch()
+```
+
+---
+
+## Intended Use
+
+`facial-age-detection` is designed for:
+
+* **Demographic Analytics** – Estimate age distributions in image datasets for research and commercial analysis.
+* **Access Control & Verification** – Enforce age-based access in digital or physical environments.
+* **Retail & Marketing** – Understand customer demographics in retail spaces through camera-based analytics.
+* **Surveillance & Security** – Enhance people classification systems by integrating age detection.
+* **Human-Computer Interaction** – Adapt experiences and interfaces based on user age.