Update app.py

app.py

@@ -3,88 +3,32 @@ import tensorflow as tf
 import numpy as np
 from PIL import Image
 
-# Load the model
-model = tf.keras.models.load_model('saved_model_cnn.keras')
+# Load the saved model
+model = tf.keras.models.load_model("saved_model_cnn.keras")
 
-# Constants
-IMG_SIZE = 224
-CLASS_NAMES = ['Gingivitis', 'Caries']
+# Define the classes
+classes = ['Gingivitis', 'Caries']
 
-def preprocess_image(image):
-    """Preprocess the uploaded image for model prediction"""
-    # If image is None, return None
-    if image is None:
-        return None
-        
-    # Convert to RGB if grayscale
-    if image.mode != 'RGB':
-        image = image.convert('RGB')
-    
-    # Resize image
-    image = image.resize((IMG_SIZE, IMG_SIZE))
-    
-    # Convert to array
-    img_array = np.array(image)
-    
-    # Add batch dimension and normalize
-    img_array = np.expand_dims(img_array, 0)
-    img_array = img_array.astype('float32') / 255.0
-    
-    return img_array
+# Prediction function
+def predict(image):
+    image = Image.fromarray(np.uint8(image)).convert("RGB")
+    image = image.resize((224, 224))  # Assuming the model expects 224x224 images
+    image_array = np.array(image) / 255.0  # Normalize to [0, 1]
+    image_array = np.expand_dims(image_array, axis=0)  # Add batch dimension
+    prediction = model.predict(image_array)
+    predicted_class = classes[np.argmax(prediction)]
+    confidence = np.max(prediction)
+    return f"Class: {predicted_class}, Confidence: {confidence:.2f}"
 
-def predict_dental_condition(image):
-    """Make prediction on the uploaded image"""
-    try:
-        # Preprocess the image
-        processed_image = preprocess_image(image)
-        
-        if processed_image is None:
-            return {
-                CLASS_NAMES[0]: 0.0,
-                CLASS_NAMES[1]: 0.0
-            }
-        
-        # Make prediction
-        prediction = model.predict(processed_image, verbose=0)
-        probability = prediction[0][0]
-        
-        # Create response dictionary
-        results = {
-            CLASS_NAMES[0]: float(1 - probability),
-            CLASS_NAMES[1]: float(probability)
-        }
-        
-        return results
-    
-    except Exception as e:
-        print(f"Error in prediction: {str(e)}")
-        return {
-            CLASS_NAMES[0]: 0.0,
-            CLASS_NAMES[1]: 0.0
-        }
-
-# Create the Gradio interface
-iface = gr.Interface(
-    fn=predict_dental_condition,
-    inputs=gr.Image(type="pil"),
-    outputs=gr.Label(num_top_classes=2),
-    title="Dental Condition Classifier",
-    description="""Upload an image of a dental condition to classify between Gingivitis and Caries.
-    This model helps identify dental conditions based on visual examination.""",
-    article="""
-    <div style="text-align: center;">
-        <p><b>How to use:</b></p>
-        <ol style="text-align: left;">
-            <li>Upload a clear image of the dental condition</li>
-            <li>Wait for the model to process the image</li>
-            <li>View the prediction results and confidence scores</li>
-        </ol>
-        <p><b>Note:</b> This is an AI assistance tool and should not replace professional medical advice.</p>
-    </div>
-    """,
-    theme=gr.themes.Soft()
+# Gradio interface
+interface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="numpy", label="Upload Image"),
+    outputs=gr.Textbox(label="Prediction"),
+    title="Dental Health Predictor",
+    description="Upload an image to predict between Gingivitis and Caries."
 )
 
 # Launch the app
 if __name__ == "__main__":
-    iface.launch()
+    interface.launch()