DX-M1 / DX-M1M SDK

This section mainly introduces application development using the DX-M1 / DX-M1M SDK for hardware-accelerated AI on Radxa AIcore DX-M1 / DX-M1M.

📄️ DX-M1 / DX-M1M SDK introduction

Overview

📄️ DX-COM model compiler

Introduction

📄️ DXRT-NPU-Driver

DXRT-NPU-Driver is the driver for Radxa AIcore DX-M1 / DX-M1M. Install this driver on the host machine that has AIcore DX-M1 / DX-M1M installed.

📄️ DX-RT runtime

DX-RT (runtime software) is the runtime used to interact with DEEPX NPU hardware. It provides pre-processing and post-processing during inference and manages NPU inputs and outputs.

📄️ DX-APP examples

DX-APP is a demo application template based on the AIcore DX-M1 / DX-M1M NPU. You can use this demo as a reference to design your own AI applications.

📄️ DX Model Zoo

DX Model Zoo provides a collection of pre-compiled DXNN models for tasks such as image classification, object detection, image segmentation, face recognition, and image denoising.

📄️ DX-Tron

DX-Tron (DXNN model viewer) is a structure viewer for DXNN models. It is developed based on Netron and supports Windows and Linux on the x86 platform.

📄️ DX-STREAM

DX-STREAM is a custom GStreamer plugin used to integrate real-time streaming data into AI inference applications based on the DEEPX NPU.