Forums
- Product Forums
  - General Purpose MicrocontrollersGeneral Purpose Microcontrollers
  - i.MX Forumsi.MX Forums
  - QorIQ Processing PlatformsQorIQ Processing Platforms
  - Identification and SecurityIdentification and Security
  - Power ManagementPower Management
  - Wireless ConnectivityWireless Connectivity
  - RFID / NFCRFID / NFC
  - Advanced AnalogAdvanced Analog
  - Neural Processing UnitsNeural Processing Units
  - MCX Microcontrollers
  - S32G
  - S32K
  - S32V
  - MPC5xxx
  - Other NXP Products
  - S12 / MagniV Microcontrollers
  - Powertrain and Electrification Analog Drivers
  - Sensors
  - Vybrid Processors
  - Digital Signal Controllers
  - 8-bit Microcontrollers
  - ColdFire/68K Microcontrollers and Processors
  - PowerQUICC Processors
  - OSBDM and TBDML
  - S32M
  - S32Z/E
- Solution Forums
- Software Forums
  - MCUXpresso Software and ToolsMCUXpresso Software and Tools
  - CodeWarriorCodeWarrior
  - MQX Software SolutionsMQX Software Solutions
  - Model-Based Design Toolbox (MBDT)Model-Based Design Toolbox (MBDT)
  - FreeMASTER
  - eIQ Machine Learning Software
  - Embedded Software and Tools Clinic
  - S32 SDK
  - S32 Design Studio
  - GUI Guider
  - Zephyr Project
  - Voice Technology
  - Application Software Packs
  - Secure Provisioning SDK (SPSDK)
  - Processor Expert Software
  - Generative AI & LLMs
- Topics
  - Mobile Robotics - Drones and RoversMobile Robotics - Drones and Rovers
  - NXP Training ContentNXP Training Content
  - University ProgramsUniversity Programs
  - Rapid IoT
  - NXP Designs
  - SafeAssure-Community
  - OSS Security & Maintenance
  - Using Our Community
- Cloud Lab Forums
  - Hardware
  - Cloud Lab Knowledge Base
Knowledge Bases
- ARM Microcontrollers
  - K32 L Series Microcontrollers Knowledge Base
  - Kinetis Microcontrollers Knowledge Base
  - Kinetis Motor Suite Knowledge Base
  - LPC FAQs Knowledge Base
  - LPC Microcontrollers Knowledge Base
  - LPCware Archive Content
  - MCX Microcontrollers Knowledge Base
- i.MX Processors
  - i.MX RT Crossover MCUs Knowledge Base
  - i.MX Graphics Knowledge Base
  - i.MX Processors Knowledge Base
  - i.MX Solutions Knowledge Base
  - i.MX 한국어 커뮤니티 Knowledge Base
- Identification and Security
  - EdgeLock 2GO Secure Service Knowledge Base
  - Secure Authentication Knowledge Base
  - Smart Cards and Secure Element Knowledge Base
- Model-Based Design Toolbox (MBDT)
- QorIQ Processing Platforms
- S32 Automotive Processing Platform
- Wireless Connectivity
  - Other Connectivity Knowledge Base
  - Wi-Fi® + Bluetooth® + 802.15.4 Knowledge Base
  - Wireless Connectivity Knowledge Base
- CodeWarrior
- MCUXpresso Suite of Software and Tools
- MQX Software Solutions
- RFID / NFC
- Advanced Analog
  - High Performance Analog Front End Interfaces
  - In Vehicle Networking
- Neural Processing Units
  - Ara DNPU Knowledge Base
- 8-bit Microcontrollers Knowledge Base
- Motor Control and Smart Energy Knowledge Base
- Power Management Knowledge Base
- FRDM Training Hub
- MCUXpresso Training Hub
- Zephyr Project Knowledge Base
- Generative AI & LLMs Knowledge Base
- Embedded World NXP Connectivity Workshop Knowledge Base
- Hands-on workshop in Japan (ハンズオン・ワークショップ [日本]) Knowledge Base
- DNPU Training Hub
NXP Tech Blogs
- NXP Tech Blog
Ideas
Blogs

Forums
Knowledge Bases
NXP Tech Blogs
NXP.COM

English (US) 日本語 | Japanese 中文 | Chinese (Simplified)

Home
:
Neural Processing Units
:
Ara DNPU Knowledge Base

Ara DNPU Knowledge Base

cancel

Turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Show only | Search instead for

Did you mean:

Options

Subscribe
Bookmark
Subscribe to RSS Feed

Ara DNPU Knowledge Base

Discussions

Sort by:

Date

Date
Views
Kudos
Comments
Helpfulness

Ara2_Model_Zoo_Compilation_Deployment_Testing_Guide

This document provides an end-to-end example for setting up the Ara2 compilation environment, compiling the YOLOv8L ONNX model with the Model Zoo, deploying the compiled model to an i.MX95 target, running inference and performance tests, and reviewing the key YAML fields that must be updated when adapting the flow to another model of the same type.

View full article

No ratings

3 weeks ago

Compile & Deployment DeepLabV3 with Ara Model Zoo v1.0.0

View full article

No ratings

3 weeks ago

Guideline for Porting a New YOLO Variant - YOLO26 on Ara2

This slides firstly introduce the YOLO26 model, and NXP Ara2 Model Zoo, Ara2 SDK/Runtime. Then it explains the CNN model compilation flow with Ara2 toolchain in SDK package, how to compile the newly added model - Yolo26n, how to setup the inference environment in i.MX95FRDM+Ara2-240 board. Finally present the inference result. Patches and user guide are provided in attachment as well.

View full article

No ratings

4 weeks ago

Study and Summary of the DNPU Model Compilation Flow

Analysis of the DNPU model compilation flow as below: (Based on Model Zoo Ara2 and SDK 2.0) Compile Flow：model_compile.sh Compile Flow：run.yaml Compile Flow：Dvconvert Compile Flow：Dvrun Compile Flow：Quantizer Compile Flow：Scheduler / Estimator Compile Flow：VPU Codegen Compile Flow：Generator / Emitter Compile Flow：Simulation Compile Flow：Accuracy Check Compile Flow：Outputs

View full article

No ratings

4 weeks ago

ARA2 User Guide for Windows Platform

Attached are the instructions for using ARA2 on the Windows platform, along with the following two project packages: factory-test-package-windows.zip qwen2.5_vl_3b_opt_ara_python_win_demo_r2.1.zip If you need any additional information or support, please feel free to contact me by email at [email protected].

View full article

No ratings

a month ago