本页翻译不是最新的。点击此处可查看最新英文版本。

微型 NPU

R2026a
使用深度学习网络和 Qualcomm® Hexagon® eNPU

Embedded Coder® Support Package for Qualcomm Hexagon Processors 提供 Simulink® 模块和 MATLAB® System object™，以使用 eAI 网络（编译的 eAI 模型）预测 eNPU 的响应，并在部署到目标之前验证 eNPU 的准确性和性能。

函数

hexagon.ENPUInterface to predict responses of eNPU using a compiled eAI model (自 R2025a 起)
hexagon.ENPU.getEAIPropertiesRead values for properties defined in eAI network file (自 R2025a 起)

模块

eNPU Predict block with an input port and output port.eNPU PredictPredict responses of eNPU using compiled eAI model (自 R2025a 起)

模型设置

Model Settings to Deploy Code for eNPU Module of Qualcomm Hexagon Processor

精选示例

Deploy Smart Speaker Model on Qualcomm Hexagon eNPU Using LPAI SDK Add-on

Deploy Smart Speaker Model on Qualcomm Hexagon eNPU Using LPAI SDK Add-on

Deploy a Simulink model designed as smart speaker system on Qualcomm Hexagon eNPU.

Convert MATLAB Deep Learning Networks to eAI Model Using Qualcomm LPAI SDK

Convert MATLAB Deep Learning Networks to eAI Model Using Qualcomm LPAI SDK

Convert deep learning networks developed using MATLAB built-in layers into eAI models for deployment to eNPU using Qualcomm LPAI SDK.