LogoLogo
HomeAPI & SDKsProjectsForumStudio
  • Getting started
    • For beginners
    • For ML practitioners
    • For embedded engineers
  • Frequently asked questions (FAQ)
  • Tutorials
    • End-to-end tutorials
      • Computer vision
        • Image classification
        • Object detection
          • Object detection with bounding boxes
          • Detect objects with centroid (FOMO)
        • Visual anomaly detection
        • Visual regression
      • Audio
        • Sound recognition
        • Keyword spotting
      • Time-series
        • Motion recognition + anomaly detection
        • Regression + anomaly detection
        • HR/HRV
        • Environmental (Sensor fusion)
    • Data
      • Data ingestion
        • Collecting image data from the Studio
        • Collecting image data with your mobile phone
        • Collecting image data with the OpenMV Cam H7 Plus
        • Using the Edge Impulse Python SDK to upload and download data
        • Trigger connected board data sampling
        • Ingest multi-labeled data using the API
      • Synthetic data
        • Generate audio datasets using Eleven Labs
        • Generate image datasets using Dall-E
        • Generate keyword spotting datasets using Google TTS
        • Generate physics simulation datasets using PyBullet
        • Generate timeseries data with MATLAB
      • Labeling
        • Label audio data using your existing models
        • Label image data using GPT-4o
      • Edge Impulse Datasets
    • Feature extraction
      • Building custom processing blocks
      • Sensor fusion using embeddings
    • Machine learning
      • Classification with multiple 2D input features
      • Visualize neural networks decisions with Grad-CAM
      • Sensor fusion using embeddings
      • FOMO self-attention
    • Inferencing & post-processing
      • Count objects using FOMO
      • Continuous audio sampling
      • Multi-impulse (C++)
      • Multi-impulse (Python)
    • Lifecycle management
      • CI/CD with GitHub Actions
      • Data aquisition from S3 object store - Golioth on AI
      • OTA model updates
        • with Arduino IDE (for ESP32)
        • with Arduino IoT Cloud
        • with Blues Wireless
        • with Docker on Allxon
        • with Docker on Balena
        • with Docker on NVIDIA Jetson
        • with Espressif IDF
        • with Nordic Thingy53 and the Edge Impulse app
        • with Particle Workbench
        • with Zephyr on Golioth
    • API examples
      • Customize the EON Tuner
      • Ingest multi-labeled data using the API
      • Python API bindings example
      • Running jobs using the API
      • Trigger connected board data sampling
    • Python SDK examples
      • Using the Edge Impulse Python SDK to run EON Tuner
      • Using the Edge Impulse Python SDK to upload and download data
      • Using the Edge Impulse Python SDK with Hugging Face
      • Using the Edge Impulse Python SDK with SageMaker Studio
      • Using the Edge Impulse Python SDK with TensorFlow and Keras
      • Using the Edge Impulse Python SDK with Weights & Biases
    • Expert network projects
  • Edge Impulse Studio
    • Organization hub
      • Users
      • Data campaigns
      • Data
        • Cloud data storage
      • Data pipelines
      • Data transformation
        • Transformation blocks
      • Upload portals
      • Custom blocks
        • Custom AI labeling blocks
        • Custom deployment blocks
        • Custom learning blocks
        • Custom processing blocks
        • Custom synthetic data blocks
        • Custom transformation blocks
      • Health reference design
        • Synchronizing clinical data with a bucket
        • Validating clinical data
        • Querying clinical data
        • Transforming clinical data
    • Project dashboard
      • Select AI hardware
    • Devices
    • Data acquisition
      • Uploader
      • Data explorer
      • Data sources
      • Synthetic data
      • Labeling queue
      • AI labeling
      • CSV Wizard (time-series)
      • Multi-label (time-series)
      • Tabular data (pre-processed & non-time-series)
      • Metadata
      • Auto-labeler | deprecated
    • Impulses
    • EON Tuner
      • Search space
    • Processing blocks
      • Audio MFCC
      • Audio MFE
      • Audio Syntiant
      • Flatten
      • HR/HRV features
      • Image
      • IMU Syntiant
      • Raw data
      • Spectral features
      • Spectrogram
      • Custom processing blocks
      • Feature explorer
    • Learning blocks
      • Anomaly detection (GMM)
      • Anomaly detection (K-means)
      • Classification
      • Classical ML
      • Object detection
        • MobileNetV2 SSD FPN
        • FOMO: Object detection for constrained devices
      • Object tracking
      • Regression
      • Transfer learning (images)
      • Transfer learning (keyword spotting)
      • Visual anomaly detection (FOMO-AD)
      • Custom learning blocks
      • Expert mode
      • NVIDIA TAO | deprecated
    • Retrain model
    • Live classification
    • Model testing
    • Performance calibration
    • Deployment
      • EON Compiler
      • Custom deployment blocks
    • Versioning
    • Bring your own model (BYOM)
    • File specifications
      • deployment-metadata.json
      • ei-metadata.json
      • ids.json
      • parameters.json
      • sample_id_details.json
      • train_input.json
  • Tools
    • API and SDK references
    • Edge Impulse CLI
      • Installation
      • Serial daemon
      • Uploader
      • Data forwarder
      • Impulse runner
      • Blocks
      • Himax flash tool
    • Edge Impulse for Linux
      • Linux Node.js SDK
      • Linux Go SDK
      • Linux C++ SDK
      • Linux Python SDK
      • Flex delegates
      • Rust Library
    • Rust Library
    • Edge Impulse Python SDK
  • Run inference
    • C++ library
      • As a generic C++ library
      • On Android
      • On your desktop computer
      • On your Alif Ensemble Series Device
      • On your Espressif ESP-EYE (ESP32) development board
      • On your Himax WE-I Plus
      • On your Raspberry Pi Pico (RP2040) development board
      • On your SiLabs Thunderboard Sense 2
      • On your Spresense by Sony development board
      • On your Syntiant TinyML Board
      • On your TI LaunchPad using GCC and the SimpleLink SDK
      • On your Zephyr-based Nordic Semiconductor development board
    • Arm Keil MDK CMSIS-PACK
    • Arduino library
      • Arduino IDE 1.18
    • Cube.MX CMSIS-PACK
    • Docker container
    • DRP-AI library
      • DRP-AI on your Renesas development board
      • DRP-AI TVM i8 on Renesas RZ/V2H
    • IAR library
    • Linux EIM executable
    • OpenMV
    • Particle library
    • Qualcomm IM SDK GStreamer
    • WebAssembly
      • Through WebAssembly (Node.js)
      • Through WebAssembly (browser)
    • Edge Impulse firmwares
    • Hardware specific tutorials
      • Image classification - Sony Spresense
      • Audio event detection with Particle boards
      • Motion recognition - Particle - Photon 2 & Boron
      • Motion recognition - RASynBoard
      • Motion recognition - Syntiant
      • Object detection - SiLabs xG24 Dev Kit
      • Sound recognition - TI LaunchXL
      • Keyword spotting - TI LaunchXL
      • Keyword spotting - Syntiant - RC Commands
      • Running NVIDIA TAO models on the Renesas RA8D1
      • Two cameras, two models - running multiple object detection models on the RZ/V2L
  • Edge AI Hardware
    • Overview
    • Production-ready
      • Advantech ICAM-540
      • Seeed SenseCAP A1101
      • Industry reference design - BrickML
    • MCU
      • Ambiq Apollo4 family of SoCs
      • Ambiq Apollo510
      • Arducam Pico4ML TinyML Dev Kit
      • Arduino Nano 33 BLE Sense
      • Arduino Nicla Sense ME
      • Arduino Nicla Vision
      • Arduino Portenta H7
      • Blues Wireless Swan
      • Espressif ESP-EYE
      • Himax WE-I Plus
      • Infineon CY8CKIT-062-BLE Pioneer Kit
      • Infineon CY8CKIT-062S2 Pioneer Kit
      • Nordic Semi nRF52840 DK
      • Nordic Semi nRF5340 DK
      • Nordic Semi nRF9160 DK
      • Nordic Semi nRF9161 DK
      • Nordic Semi nRF9151 DK
      • Nordic Semi nRF7002 DK
      • Nordic Semi Thingy:53
      • Nordic Semi Thingy:91
      • Open MV Cam H7 Plus
      • Particle Photon 2
      • Particle Boron
      • RAKwireless WisBlock
      • Raspberry Pi RP2040
      • Renesas CK-RA6M5 Cloud Kit
      • Renesas EK-RA8D1
      • Seeed Wio Terminal
      • Seeed XIAO nRF52840 Sense
      • Seeed XIAO ESP32 S3 Sense
      • SiLabs Thunderboard Sense 2
      • Sony's Spresense
      • ST B-L475E-IOT01A
      • TI CC1352P Launchpad
    • MCU + AI accelerators
      • Alif Ensemble
      • Arduino Nicla Voice
      • Avnet RASynBoard
      • Seeed Grove - Vision AI Module
      • Seeed Grove Vision AI Module V2 (WiseEye2)
      • Himax WiseEye2 Module and ISM Devboard
      • SiLabs xG24 Dev Kit
      • STMicroelectronics STM32N6570-DK
      • Synaptics Katana EVK
      • Syntiant Tiny ML Board
    • CPU
      • macOS
      • Linux x86_64
      • Raspberry Pi 4
      • Raspberry Pi 5
      • Texas Instruments SK-AM62
      • Microchip SAMA7G54
      • Renesas RZ/G2L
    • CPU + AI accelerators
      • AVNET RZBoard V2L
      • BrainChip AKD1000
      • i.MX 8M Plus EVK
      • Digi ConnectCore 93 Development Kit
      • MemryX MX3
      • MistyWest MistySOM RZ/V2L
      • Qualcomm Dragonwing RB3 Gen 2 Dev Kit
      • Renesas RZ/V2L
      • Renesas RZ/V2H
      • IMDT RZ/V2H
      • Texas Instruments SK-TDA4VM
      • Texas Instruments SK-AM62A-LP
      • Texas Instruments SK-AM68A
      • Thundercomm Rubik Pi 3
    • GPU
      • Advantech ICAM-540
      • NVIDIA Jetson
      • Seeed reComputer Jetson
    • Mobile phone
    • Porting guide
  • Integrations
    • Arduino Machine Learning Tools
    • AWS IoT Greengrass
    • Embedded IDEs - Open-CMSIS
    • NVIDIA Omniverse
    • Scailable
    • Weights & Biases
  • Tips & Tricks
    • Combining impulses
    • Increasing model performance
    • Optimizing compute time
    • Inference performance metrics
  • Concepts
    • Glossary
    • Course: Edge AI Fundamentals
      • Introduction to edge AI
      • What is edge computing?
      • What is machine learning (ML)?
      • What is edge AI?
      • How to choose an edge AI device
      • Edge AI lifecycle
      • What is edge MLOps?
      • What is Edge Impulse?
      • Case study: Izoelektro smart grid monitoring
      • Test and certification
    • Data engineering
      • Audio feature extraction
      • Motion feature extraction
    • Machine learning
      • Data augmentation
      • Evaluation metrics
      • Neural networks
        • Layers
        • Activation functions
        • Loss functions
        • Optimizers
          • Learned optimizer (VeLO)
        • Epochs
    • What is embedded ML, anyway?
    • What is edge machine learning (edge ML)?
Powered by GitBook
On this page
  • Installing dependencies
  • Connecting to Edge Impulse
  • Next steps: building a machine learning model
  • Deploying back to device
  • DRP-AI TVM i8 library

Was this helpful?

Export as PDF
  1. Edge AI Hardware
  2. CPU + AI accelerators

Renesas RZ/V2H

PreviousRenesas RZ/V2LNextIMDT RZ/V2H

Last updated 2 months ago

Was this helpful?

The RZ/V2H high-end AI MPU boasts Renesas' proprietary dynamically reconfigurable processor AI accelerator (DRP-AI3), quad Arm® Cortex®-A55 (1.8GHz) Linux processors, and dual Cortex®-R8 (800MHz) real-time processors. Furthermore, the RZ/V2H also includes another dynamically reconfigurable processor (DRP). This processor can accelerate image processing, such as OpenCV, and dynamics calculations required for robotics applications. It also features high-speed interfaces like PCIe®, USB 3.2, and Gigabit Ethernet, making it an ideal microprocessor for applications such as autonomous robots and machine vision in factory automation, where advanced AI processing must be implemented with low power consumption.

The RZ/V2H EVK provides a USB serial interface, 2 channel Ethernet interfaces, four camera interfaces and an HDMI display interface, in addition to many other interfaces (PMOD, microphone, audio output, etc.). The RZ/V2H EVK can be acquired directly through the Renesas website.

The Renesas RZ/V2H board realizes hardware acceleration through the DRP-AI IP that consists of a Dynamically Configurable Processor (DRP), and Multiply and Accumulate unit (AI-MAC). The DRP-AI IP is designed to process the entire neural network plus the required pre- and post-processing steps. Additional optimization techniques reduce power consumption and increase processing performance. This leads to high power efficiency and allows using the MPU without a heat sink.

Note that, the DRP-AI is designed for feed-forward neural networks that are usually in vision-based architectures. For more information about the DRP-AI, please refer to the white paper published by the Renesas team.

The Renesas tool “DRP-AI TVM” is used to translate machine learning models and optimize the processing for DRP-AI. The tool is fully supported by Edge Impulse. This means that machine learning models downloaded from the studio can be directly deployed to the RZ/V2H board.

For more technical information about RZ/V2H, please refer to the Renesas RZ/V2H documentation and for the RZ/V2H-EVK.

Installing dependencies

Yocto image preparation/patch/build for V2H

Renesas provides Yocto build system to build all the necessary packages and create the Linux image. The Renesas documentation calls out that the build system must be based off of Ubuntu 20.04. The following instructions here outline the necessary steps to setup your build environment.

In order to use the Edge Impulse CLI tools, NodeJS v18 needs to be installed into the yocto image that you build. You will need to download the required NodeJS v18 patch here. Given the instructions called out here, once the following file must be downloaded from Renesas (specific versions specified are required):

RTK0EF0180F05000SJ_linux-src.zip

After downloaded, you should have these two files in your directory:

nodejs_patches_for_EdgeImpulse_20240805.tar.gz
RTK0EF0180F05000SJ_linux-src.zip

Next we need to download a specific layer from Edge Impulse to properly setup/install the DRP-AI and TVM SDK. The zip file for the layer can be downloaded from here. Once downloaded, you will then place the file into the same directory as the RTK0EF0180F05000SJ_linux-src.zip above.

Next, you will need to create and patch your V2H yocto build environment as follows (this can be exported into a script that can be run):

#!/bin/bash

set -x
DIR=`pwd`
# Go to the directory that you have downloaded all of the above files into... then:
mkdir ./archive
mv RTK* ./archive
mv nodejs_patches*gz ./archive
mv meta-ei.zip ./archive
cd ./archive
tar xzpf ./nodejs_patches_for_EdgeImpulse_20240805.tar.gz
cd $DIR
unzip ./archive/RTK0EF0180F05000SJ_linux-src.zip
tar zxf rzv2h_ai-sdk_yocto_recipe_v5.00.tar.gz
unzip ./archive/meta-ei.zip
cd $DIR
TEMPLATECONF=$DIR/meta-renesas/meta-rzv2h/docs/template/conf/
export MACHINE=rzv2h-evk-ver1
source poky/oe-init-build-env
cd $DIR/build
bitbake-layers add-layer ../meta-rz-features/meta-rz-graphics
bitbake-layers add-layer ../meta-rz-features/meta-rz-drpai
bitbake-layers add-layer ../meta-rz-features/meta-rz-opencva
bitbake-layers add-layer ../meta-rz-features/meta-rz-codecs
bitbake-layers add-layer ../meta-openembedded/meta-filesystems
bitbake-layers add-layer ../meta-openembedded/meta-networking
bitbake-layers add-layer ../meta-virtualization
bitbake-layers add-layer ../meta-ei
patch -p1 < ../0001-tesseract.patch
cd ${DIR}/meta-openembedded/meta-oe/recipes-devtools/
tar -zxvf ${DIR}/archive/nodejs_patches_for_EdgeImpulse/nodejs_18.17.1.tar.gz
mv nodejs nodejs_12.22.12
ln -s nodejs_18.17.1 nodejs
cd ${DIR}
cd ${DIR}/poky/meta/recipes-support/
tar -zxvf ${DIR}/archive/nodejs_patches_for_EdgeImpulse/icu_70.1.tar.gz
mv icu icu_66.1
ln -s icu_70.1 icu
cd $DIR/build
echo ""                                     >> ./conf/local.conf
echo "IMAGE_INSTALL_append = \" \\"         >> ./conf/local.conf
echo "    nodejs \\"                        >> ./conf/local.conf
echo "    nodejs-npm \\"                    >> ./conf/local.conf
echo "    \""                               >> ./conf/local.conf
echo ""                                     >> ./conf/local.conf
echo ""                                     >> ./conf/local.conf
echo "IMAGE_INSTALL_append = \" \\"         >> ./conf/local.conf
echo "    nvme-cli \\"                      >> ./conf/local.conf
echo "    sudo \\"                          >> ./conf/local.conf
echo "    curl \\"                          >> ./conf/local.conf
echo "    zlib \\"                          >> ./conf/local.conf
echo "    drpaitvm \\"                      >> ./conf/local.conf
echo "    binutils \\"                      >> ./conf/local.conf
echo "    \""                               >> ./conf/local.conf
echo ""                                     >> ./conf/local.conf
#
# Extra image configuration defaults
#
# The EXTRA_IMAGE_FEATURES variable allows extra packages to be added to the generated
# images. Some of these options are added to certain image types automatically. The
# variable can contain the following options:
#  "dbg-pkgs"       - add -dbg packages for all installed packages
#                     (adds symbol information for debugging/profiling)
#  "src-pkgs"       - add -src packages for all installed packages
#                     (adds source code for debugging)
#  "dev-pkgs"       - add -dev packages for all installed packages
#                     (useful if you want to develop against libs in the image)
#  "ptest-pkgs"     - add -ptest packages for all ptest-enabled packages
#                     (useful if you want to run the package test suites)
#  "tools-sdk"      - add development tools (gcc, make, pkgconfig etc.)
#  "tools-debug"    - add debugging tools (gdb, strace)
#  "eclipse-debug"  - add Eclipse remote debugging support
#  "tools-profile"  - add profiling tools (oprofile, lttng, valgrind)
#  "tools-testapps" - add useful testing tools (ts_print, aplay, arecord etc.)
#  "debug-tweaks"   - make an image suitable for development
#                     e.g. ssh root access has a blank password
# There are other application targets that can be used here too, see
# meta/classes/image.bbclass and meta/classes/core-image.bbclass for more details.
#
echo "WHITELIST_GPL-3.0 += \" cpp gcc gcc-dev mpfr g++ cpp make make-dev binutils libbfd \""             >> ./conf/local.conf
echo "IMAGE_INSTALL_append = \" zlib gcc g++ make cpp packagegroup-core-buildessential \""               >> ./conf/local.conf
echo "IMAGE_INSTALL_append = \" python3 python3-pip python3-core python3-modules \""                     >> ./conf/local.conf
echo "IMAGE_INSTALL_append = \" gstreamer1.0 gstreamer1.0-plugins-base gstreamer1.0-plugins-good \""     >> ./conf/local.conf
echo "IMAGE_INSTALL_append = \" gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly \""                   >> ./conf/local.conf
echo "EXTRA_IMAGE_FEATURES ?= \" debug-tweaks dev-pkgs tools-debug tools-sdk \""                         >> ./conf/local.conf
echo "DISTRO_FEATURES ?= \" usbgadget usbhost wifi opengl \""                                            >> ./conf/local.conf
echo "IMAGE_ROOTFS_EXTRA_SPACE_append_qemuall = \" + 3000000\""                                          >> ./conf/local.conf
#-# glibc2.31 instead of glibc2.28
sed -i 's/^CIP_MODE = "Buster"/CIP_MODE = "Bullseye"/g' ./conf/local.conf

You can then invoke your V2H yocto build process via:

#!/bin/bash

set -x
DIR=`pwd`
export TEMPLATECONF=$DIR/meta-renesas/meta-rzv2h/docs/template/conf/
export MACHINE=rzv2h-evk-ver1
source poky/oe-init-build-env
time bitbake core-image-weston

Renesas documentation here then shows you different build options + how to flash your compiled images onto your V2H board. Once your build completes, your files that will be used in those subsequent instructions called out here to flash your V2H board can be found here:

#!/bin/bash

DIR=`pwd`
ls -al $DIR/build/tmp/deploy/images/rzv2h-evk-ver1

Post-flashing tasks

Once your RZ V2H board is running your new image, you will need to complete an additional task. Please perform the following to setup the DRP-AI and TVM SDK:

# cd /usr/drpaitvm
# ./ei_install.sh

Your RZ V2H board should now be ready to run an EI model optimized for DRP-AI and TVM!

Accessing the board using screen

The easiest way is to connect through serial to the RZ/V2H board using the USB mini b port.

  1. After connecting the board with a USB-C cable, please power the board.

  2. Power on the board: Connect the power cable to the board, switch SW3 ON then SW2 ON.

  3. Please install screen to the host machine and then execute the following command from Linux to access the board:

    screen /dev/ttyUSB0 115200
  4. You will see the boot process, then you will be asked to log in:

    • Log in with username root

    • There is no password

Note that, it should be possible to use an Ethernet cable and log in via SSH if the daemon is installed on the image. However, for simplicity purposes, we do not refer to this one here.

Installing Edge Impulse Linux CLI

Once you have logged in to the board, please run the following command to install Edge Impulse Linux CLI

npm install edge-impulse-linux -g --unsafe-perm

Connecting to Edge Impulse

With all software set up, connect your USB camera (or a supported MIPI CSI camera) to your Renesas board (see 'Next steps' further on this page if you want to connect a different sensor), and run:

edge-impulse-linux

This will start a wizard which will ask you to log in and choose an Edge Impulse project. If you want to switch projects run the command with --clean.

Verifying that your device is connected

That's all! Your device is now connected to Edge Impulse. To verify this, go to your Edge Impulse project, and click Devices. The device will be listed here.

Next steps: building a machine learning model

Currently, all Edge Impulse models can run on the RZ/V2H CPU which is a dedicated Cortex A55. In addition, you can bring your own model to Edge Impulse and use it on the device. However, if you would like to benefit from the DRP-AI3 hardware acceleration support including higher performance and power efficiency, please use one of the following models:

For object detection:

  • Yolov5 (v5)

  • FOMO (Faster objects More Objects)

For Image classification:

  • MobileNet v1, v2

It supports as well models built within the studio using the available layers on the training page.

Note that, on the training page you have to select the target before starting the training in order to tell the studio that you are training the model for the RZ/V2H. This can be done on the top right in the training page.

If you would like to do object detection with Yolov5 (v5) you need to fix the image resolution in the impulse design to 320x320, otherwise, you might risk that the training fails.

With everything set up you can now build your first machine learning model with these tutorials:

  • Image classification.

  • Detect objects using FOMO.

Deploying back to device

To run your impulse locally, just connect to your Renesas RZ/V2H and run:

edge-impulse-linux-runner 

This will automatically compile your model with full hardware acceleration and download the model to your Renesas board, and then start classifying.

Or you can select the RZ/V2H board from the deployment page, this will download an eim model that you can use with the above runner as follows:

Go to the deployment page and select:

Then run the following on the RZ/V2H:

edge-impulse-linux-runner --model-file downloaded-model.eim

You will see the model inferencing results in the terminal also we stream the results to the local network. This allows you to see the output of the model in real-time in your web browser. Open the URL shown when you start the runner and you will see both the camera feed and the classification results.

DRP-AI TVM i8 library

Since the RZ/V2H benefits from hardware acceleration using the DRP-AI, we provide you with the drp-ai-tvm-i8 library that uses our C++ Edge Impulse SDK, DRP-AI TVM and models headers that run on the hardware accelerator. If you would like to integrate the model source code into your applications and benefit from the DRP-AI then you need to select the drp-ai-tvm-i8 library.

We have an example showing how to use the drp-ai-tvm-i8 library that can be found in Deploy your model as a DRP-AI TVM i8 library.

Renesas RZ/V2H
Device connected to Edge Impulse.
Selecting the target from the training page
EIM model for the RZ/V2H
DRP-AI TVM i8 library