Update app.py

app.py

@@ -1,26 +1,36 @@
-# prompt: use this model, https://huggingface.co/liriope/PlantDiseaseDetection, create app.py for implementing this on gradio
+
 
 import gradio as gr
-from transformers import pipeline
+from transformers import pipeline, AutoImageProcessor, AutoModelForImageClassification
+from PIL import Image
+
+# Load the pre-trained model and image processor
+model_name = "Diginsa/Plant-Disease-Detection-Project"
+processor = AutoImageProcessor.from_pretrained(model_name)
+model = AutoModelForImageClassification.from_pretrained(model_name)
 
-# Load the pre-trained model
-pipe = pipeline("image-classification", model="liriope/PlantDiseaseDetection")
+# Create the prediction pipeline
+pipe = pipeline("image-classification", model=model, image_processor=processor)
 
-def classify_image(image):
+def predict_disease(image):
+    """Predicts the plant disease based on the input image."""
     predictions = pipe(image)
-    result = ""
+    
+    # Format the predictions for display
+    results = []
     for pred in predictions:
-        label = pred["label"]
-        score = pred["score"]
-        result += f"{label}: {score:.4f}\n"
-    return result
+        results.append(f"{pred['label']}: {pred['score']:.4f}")
+    
+    return "\n".join(results)  # Return predictions as a single string
 
+# Create the Gradio interface
 iface = gr.Interface(
-    fn=classify_image,
-    inputs=gr.Image(type="pil"),
-    outputs="text",
-    title="Plant Disease Classifier",
-    description="Upload an image to classify the plant disease.",
+    fn=predict_disease,
+    inputs=gr.Image(type="pil"),  # Input is a PIL Image
+    outputs="text",  # Output is a text string with predictions
+    title="Plant Disease Detection",
+    description="Upload an image of a plant to detect potential diseases.",
 )
 
-iface.launch(debug=True)
+# Launch the Gradio interface
+iface.launch()