Detector Recipes Overview

The LEIP SDK provides recipes for an assortment of Image Detector models that cover a range of applications depending on the requirements for your use case. The following pages walk you through a tutorial on how to get started using recipes. We will start with the most basic example: generating the pre-trained YOLOv5 model we used to get the benchmarks in our recent blog post. We also provide several EfficientDet and MobileNet SSD detector recipes. We recommend following the YOLOv5 example first to get familiar with the process.

We will skip training the model with your own data for now. The model provided has been pre-trained with the MS COCO dataset and is suitable for many applications. Refer to the section on adding your own data if you would prefer to retrain the model.

Let us begin by evaluating and exporting a YOLOv5 model.