Update app.py

app.py

@@ -9,20 +9,26 @@ model_path = 'final_teath_classifier.h5'
 model = tf.keras.models.load_model(model_path)
 # Define prediction function
 def predict_image(image):
-    image = image.resize((256, 256))
-    img_array = np.array(image) / 255.0
-    img_array = np.expand_dims(img_array, axis=0)
-    outputs = model.predict(img_array)
-    predictions = tf.nn.softmax(outputs.logits, axis=-1)
-    predicted_class_index = np.argmax(predictions)
-    
-    # Map class index to label
-    if predicted_class_index == 0:
-        predicted_label = "Clean"
-    else:
-        predicted_label = "Carries"
-    
-    return {"prediction": predicted_label}
+    image_bytes = io.BytesIO()
+    image.save(image_bytes, format="JPEG")
+
+    # Load the image from the file-like object
+    image = tf.keras.preprocessing.image.load_img(image_bytes, target_size=(256, 256))
+    image = tf.keras.preprocessing.image.img_to_array(image)
+    image = np.expand_dims(image, axis=0)
+
+    # Make a prediction
+    prediction = model.predict(image)
+
+    # Get the probability of being 'Good'
+    probability_good = prediction[0][0]  # Assuming it's a binary classification
+
+    # Define the prediction result
+    result = {
+        "prediction": "Your Teeth are Good & You Don't Need To Visit Doctor" if probability_good > 0.5 else "Your Teeth are Bad & You Need To Visit Doctor"
+    }
+
+    return result
 
 # Create the interface
 input_interface = gr.Image(type="pil")