Update README.md

README.md

@@ -4,6 +4,11 @@ datasets:
 - viola77data/recycling-dataset
 library_name: transformers
 ---
+
+# **Recycling-Net-11**
+
+> **Recycling-Net-11** is an image classification model fine-tuned from **google/siglip2-base-patch16-224** using the **SiglipForImageClassification** architecture. The model classifies images into 11 categories related to recyclable materials, helping to automate and enhance waste sorting systems.
+
 ```py
 Classification Report:
                    precision    recall  f1-score   support
@@ -25,4 +30,91 @@ disposable plates     0.9078    0.9744    0.9399       273
      weighted avg     0.9127    0.9128    0.9119      3107
 ```
 
-![download.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/XW6fZXkQ2-Z5KhSjnxuQs.png)
+![download.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/XW6fZXkQ2-Z5KhSjnxuQs.png)
+
+The model categorizes images into the following classes:
+
+- **0:** aluminium  
+- **1:** batteries  
+- **2:** cardboard  
+- **3:** disposable plates  
+- **4:** glass  
+- **5:** hard plastic  
+- **6:** paper  
+- **7:** paper towel  
+- **8:** polystyrene  
+- **9:** soft plastics  
+- **10:** takeaway cups  
+
+---
+
+# **Run with Transformers 🤗**
+
+```python
+!pip install -q transformers torch pillow gradio
+```
+
+```python
+import gradio as gr
+from transformers import AutoImageProcessor, SiglipForImageClassification
+from PIL import Image
+import torch
+
+# Load model and processor
+model_name = "prithivMLmods/Recycling-Net-11"  # Update with your actual Hugging Face model path
+model = SiglipForImageClassification.from_pretrained(model_name)
+processor = AutoImageProcessor.from_pretrained(model_name)
+
+# Label mapping
+id2label = {
+    0: "aluminium",
+    1: "batteries",
+    2: "cardboard",
+    3: "disposable plates",
+    4: "glass",
+    5: "hard plastic",
+    6: "paper",
+    7: "paper towel",
+    8: "polystyrene",
+    9: "soft plastics",
+    10: "takeaway cups"
+}
+
+def classify_recyclable_material(image):
+    """Predicts the type of recyclable material in the 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 = {id2label[i]: round(probs[i], 3) for i in range(len(probs))}
+    return predictions
+
+# Gradio interface
+iface = gr.Interface(
+    fn=classify_recyclable_material,
+    inputs=gr.Image(type="numpy"),
+    outputs=gr.Label(label="Recyclable Material Prediction Scores"),
+    title="Recycling-Net-11",
+    description="Upload an image of a waste item to identify its recyclable material type."
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()
+```
+
+---
+
+# **Intended Use**
+
+**Recycling-Net-11** is ideal for:
+
+- **Smart Waste Sorting:** Automating recycling processes in smart bins or factories.  
+- **Environmental Awareness Tools:** Helping people learn how to sort waste correctly.  
+- **Municipal Waste Management:** Classifying and analyzing urban waste data.  
+- **Robotics:** Assisting robots in identifying and sorting materials.  
+- **Education:** Teaching children and communities about recyclable materials.