User Guide

EdgeBench is a cloud-based platform designed to streamline the evaluation and benchmarking of AI/ML models on Analog Devices (ADI) embedded hardware. It eliminates the complexities traditionally associated with embedded AI development such as hardware setup, tools setup, and model deployment by offering a browser-accessible interface that enables remote compilation, deployment, and performance analysis.

Watch

EdgeBench Demo Video Using a Model from the Model Zoo

• About
• Logging In
• Application Overview
• Navigating the Workspace
• Workspace Tasks
• Exploring Model Zoo
• Preparing for BYOM
• Exporting Builds for Codefusion Studio
• Build Process Overview
• Build Step 1 - Device Selection
• Build Step 2 - Configure and Compile
• Build Step 3 - Upload Input Data
• Build Step 4 - Pre-Processing Script
• Build Step 5 - Post-Processing Script
• Build Step 6 - Deploy and Inference
• Build Step 7 - Inference Results

Note

You can toggle between light and dark mode using the sun and moon icons on the top right of the page.