Maintaining your fastai model
Deploying a model is not the end of the story. Once you have deployed a model, you need to maintain the deployment so that it matches the current characteristics of the data on which the model is trained. A thorough description of how to maintain a deep learning model in production is beyond the scope of this book, but it is worthwhile to touch on how to maintain models in the context of the simple model deployments described in this chapter. In this recipe, we will look at actions you could take to maintain the tabular model that you deployed in the Deploying a fastai model trained on a tabular dataset recipe.
Getting ready
Ensure that you have followed the steps in the Setting up fastai on your local system recipe to get fastai installed on your local system. Also ensure that you have the Flask server started for the tabular model deployment by following Steps 1, 2, and 3 from the Deploying a fastai model trained on a tabular dataset recipe.
...
