zscore_transform

    @staticmethod
    def get_embedding(model, face_pixels):
        """
            Normalizes the image and uses the model to produce features.

            input:
                model - The model that creates the features. This should be the FaceNet model
                face_pixels - The cropped face image.

            output:
                yhat - The features for a face. This should produce 128 features with FaceNet.
        """
        face_pixels = face_pixels.astype('float32')
        # standardize pixel values across channels (global)
        mean, std = face_pixels.mean(), face_pixels.std()
        face_pixels = (face_pixels - mean) / std
        # transform face into one sample
        samples = expand_dims(face_pixels, axis=0)
        # make prediction to get embedding
        yhat = model.predict(samples)
        return yhat[0]