Create augmented_waste_classifier.py

augmented_waste_classifier.py

@@ -0,0 +1,45 @@
+import gradio as gr
+import spaces
+from transformers import AutoImageProcessor
+from transformers import SiglipForImageClassification
+from transformers.image_utils import load_image
+from PIL import Image
+import torch
+
+# Load model and processor
+model_name = "prithivMLmods/Augmented-Waste-Classifier-SigLIP2"
+model = SiglipForImageClassification.from_pretrained(model_name)
+processor = AutoImageProcessor.from_pretrained(model_name)
+
+@spaces.GPU
+def waste_classification(image):
+    """Predicts waste classification for 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()
+    
+    labels = {
+        "0": "Battery", "1": "Biological", "2": "Cardboard", "3": "Clothes", 
+        "4": "Glass", "5": "Metal", "6": "Paper", "7": "Plastic", 
+        "8": "Shoes", "9": "Trash"
+    }
+    predictions = {labels[str(i)]: round(probs[i], 3) for i in range(len(probs))}
+    
+    return predictions
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=waste_classification,
+    inputs=gr.Image(type="numpy"),
+    outputs=gr.Label(label="Prediction Scores"),
+    title="Augmented Waste Classification",
+    description="Upload an image to classify the type of waste."
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()