Qualcomm AI Engine Direct
使用深度学习网络和 Qualcomm AI Engine Direct 后端
Qualcomm AI Engine Direct SDK（通常称为 QNN SDK (Qualcomm Neural Network SDK)）便于跨其他处理单元（如 CPU、NPU、LPAI（低功耗 AI）、DSP 和 GPU，统称为后端）使用各种接口和工件。有关详细信息，请参考 Qualcomm 文档。
Embedded Coder® Support Package for Qualcomm® Hexagon® Processors 提供 Simulink® 模块和 MATLAB® System object，用于使用 QNN 主机模型和目标模型预测后端响应，并在部署到后端之前验证准确度和性能。
函数
qnn.getNetworkProperties | Read values for properties defined in QNN model or QNN context binary file (自 R2025b 起) |
对象
qnn.CPU | Interface to predict responses of deep learning model for QNN CPU backend (自 R2025b 起) |
qnn.DSP | Interface to predict responses of deep learning model for QNN DSP backend (自 R2026a 起) |
qnn.GPU | Interface to predict responses of deep learning model for QNN GPU backend (自 R2026a 起) |
qnn.HTP | Interface to predict responses of deep learning model for QNN HTP backend (自 R2025b 起) |
qnn.LPAI | Interface to predict responses of deep learning model for QNN LPAI backend (自 R2025b 起) |
模块
| QNN CPU Predict | Predict responses of QNN model for CPU backend (自 R2025b 起) |
| QNN DSP Predict | Predict responses of QNN model for DSP backend (自 R2026a 起) |
| QNN GPU Predict | Predict responses of QNN model for GPU backend (自 R2026a 起) |
| QNN HTP Predict | Predict responses of QNN model or QNN context binary for HTP (NPU) backend (自 R2025b 起) |
| QNN LPAI Predict | Predict responses of QNN context binary for LPAI backend (自 R2025b 起) |
主题
- Troubleshoot Qualcomm AI Engine Direct Setup for Windows and Linux
Troubleshoot issues in Qualcomm AI Direct Engine setup.
精选示例
Deploy Deep Neural Networks to Qualcomm Targets Using Qualcomm AI Engine Direct (QNN)
Learn the workflow for using the Simulink blocks under the QNN Simulink library.
全新
Deploy YOLOX Object Detection and Tracking System on Qualcomm Hexagon NPU
Deploy a YOLOX-based real-time object detection and tracking system on Qualcomm Hexagon NPU using the Qualcomm AI Engine Direct (QNN) SDK.
