Update app.py

app.py

@@ -10,14 +10,7 @@ model_path = 'final_teath_classifier.h5'
 model = tf.keras.models.load_model(model_path)
 
 # Define preprocessing function
-def preprocess_image(image):
-    # Resize the image to match input size
-    #image = image.resize((256, 256))
-    # Convert image to array and preprocess input
-    image = tf.keras.preprocessing.image.img_to_array(image)
-    # Add batch dimension
-    img_array = np.expand_dims(image, axis=0)
-    return img_array
+
 
 # Define prediction function
 def predict_image(image):
@@ -26,7 +19,8 @@ def predict_image(image):
     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))
-    img_array = preprocess_image(image)
+    image = tf.keras.preprocessing.image.img_to_array(image)
+    img_array = np.expand_dims(image, axis=0)
     outputs = model.predict(img_array)
     predictions = tf.nn.softmax(outputs.logits, axis=-1)
     predicted_class = np.argmax(predictions)
@@ -36,7 +30,9 @@ def predict_image(image):
         predict_label = "Carries"
     confidence = float(np.max(predictions))
     prediction_dict = {"prediction": predict_label, "confidence": confidence}
-    return prediction_dict
+    #return prediction_dict
+    probability_good = outputs[0][0]
+    return probability_good
 
 # Create the interface
 input_interface = gr.Image(type = "pil")