In production, we need to create an endpoint so our users can send the image and receive the result. In TensorFlow, we can easily serve our model with TensorFlow Serving. In this section, we will install TensorFlow Serving and create a Flask app that allows users to upload their images via a web interface.
Serving the model in production
Setting up TensorFlow Serving
In your production server, you need to install TensorFlow Serving and its prerequisites. You can visit the official website of TensorFlow Serving at https://tensorflow.github.io/serving/setup. Next, we will use the standard TensorFlow Model Server provided in TensorFlow Serving to serve the model. First, we need to build the tensorflow_model_server with the following...