FPGA AI Suite: Getting Started Guide

ID 768970
Date 3/29/2024
Document Table of Contents

6.12. Performing Inference on YOLOv3 and Calculating Accuracy Metrics

This tutorial targets Arria® 10 devices and assumes that you have the following prerequisites completed:

To target this tutorial to a different FPGA device, you can adjust the commands appropriately (such as using a a different architecture file like AGX7_Performance.arch to target Agilex™ 7 devices). Be sure that you are using an architecture file that includes support for YOLOv3 (and specifically the PReLU activation).

The steps in the sections that follow guide you through preparing a YOLOv3 model for inference, preparing a COCO validation dataset and annotations, as well as calculating mAP and COCO AP metrics.