The LEIP SDK currently provides a large number of Classifier Recipes using a single base configuration file. This configuration file supports a number of classifier backbones that have been qualified to ensure that they compress and compile for common hardware targets. The following tutorial walks through an example where we train and evaluate some of these models on a small open images dataset. This dataset will enable us to quickly demonstrate each step of the process and give us a decent baseline accuracy for verification purposes.
Let us begin by evaluating and exporting a single classifier model.