General Information

Official RZ/V2H Device Website *
- Product Page
- RZ/V AI SDK
- Handbook ( aka Easy Download Guide )
- AI accelerator (DRP-AI3) supporting up to 80TOPS AI performance
Evaluation Board Documentation
- RZ/V2H Quad-core Vision AI MPU Evaluation Kit
Software Downloads
- Check "Software & Tool Pages" section on on this page
- RZ/V2H Linux Package
- Mali Graphic Library
- Video Codec Library
- ARM Mali Full ISP
- RZ/V2L DRP-AI Support Package
- RZ/V2H Cortex-M33 and Cortex-CR8 Multi-OS Package (optional)
- Robotic Operating System (ROS)
- RZ/V2H Cortex CM33 FSP

Board Hardware

RZ/V2H AI SDK Getting Started

Requirements

100W USBC Power Block
100W USBC Cable
USB Mini-AI Cable ( Serial Monitor )
HDMI Cable for Display

eSD Bootloader

xSPI Bootloader

eMMC Bootloader

No eMMC on the RZ/V2H EVK

Prebuilt Images

RZ/V2H AI SDK

To help expedite evaluation of the RZ/V2H we provide Pre-build Images of the RZ/V2H VLP.
- RZ/V2H AI SDK V5.0
- RZ/V2H AI SDK V4.0
- RZ/V2H AI SDK v3.0

AI SDK Contents:

eSD Card Image

- The eSD Card Image is a prebuilt yocto image that contains the following yocto packages
  - VLP Linux
  - ARM Mali Graphics ( limited license )
  - Codec ( limited license )
  - DRP-AI Driver
  - OpenCVA ( DRP Accelerated )
- The eSD Image DOES NOT include the following
  - e-CON MIPI Camera ( Contact e-CON Systems )
  - AI SDK Demos ( Coming Soon )

TVM Translator Environment

- The TVM Translator is the recommended translator to translate AI models for the DRP-AI Driver. All the AI SDK demos use the TVM Translator. Included in the AI SDK is the DRP-AI Translator. This translator is needed for TVM installation and does not need to be installed. Installation using Docker is recommended because the TVM Environment requires a PC running Ubuntu 20.04. For information about Docker setup see here.
- For information about using the TVM Translator see the Official Site here.
- NOTE: Once the AI SDK Environment is setup the TVM will be installed in the the root directory /drp_tvm_sdk

Available Demos

DRP-AI

vSLAM (Contact Sales Representative for demo)
DRP-AI Demos
- Included with the DRP-AI Package. AI models include
  - Classification (Resnet50)
  - Object Detection ( YoloX and Yolov2 )
  - Segmentation ( DeepLabv2 )
Renesas RZ/V2H AI SDK

AI SDK Application Repository

The AI SDK repository contains many AI Demos. This repo contains source, pre-compiled application, and Translated AI Models for DRP-AI. This make the repository very large. Below is a method to download single demo

Download R01_object_detection

git clone --depth 1 --filter=blob:none --sparse \
  https://github.com/renesas-rz/rzv_ai_sdk.git
cd test-git-partial-clone-big-small
git sparse-checkout set R01_object_detection

RZ/V2H vSLAM Sample Code

This is a YOLO-Planar-SLAM-DRP system developed based on YoloPlanarSLAM.
This SLAM can improve tracking accuracy by removing moving object (human) with object detection AI model (YOLO).
Renesas' high-performance AI accelerator (DRP-AI) enable to operate YOLO in real-time.
Visual AI SLAM Solution Guide here
By company Computermind demo

DRP-AI Tools

DRP-AI TVM Tool ^{by EdgeCortix}

DRP-AI TVM wiki

DRP-AI Application Development

The Renesas TVM is the DRP-AI translator tool used to convert standard ML Frameworks ( Pytorch, Tensorflow, ONNX, .. ) to DRP-AI Hardware object files. The TVM for RZ/V2N includes the following tools. This is the recommended tool for AI Model Translation to the DRP-AI.

AI Model to DRP-AI Hardware Translation Flow. For Sparse Model Creation the recommended path after ML Framework is S1, S2, S3. For Dense Model Creation after ML Framework is D1, D2.

⚠️ The DRP-AI Tools will only work in Ubuntu 20.04

⚠️ the flow S1 is using the pruning CLI tool. The Pruning tool also includes python expansion pack, so S1 can be integrated into the ML Framework training step.

Dense Model Translation

Translate a Model with out optimization

Step D1 ) Quantization.

Required for RZ/V2H
Translates a model hyper parameters to U8INT.
Requires additional AI Learning. Test Data Set should be sufficient.
Included in the DRP-AI TVM

Step D2 ) Translation

This Auto Tool, ( no special language )
Converts the Tensorflow, Tensorflowlite, Pytorch. etc. to DRP-AI code
Output is a series of Binary and Configuration files required by the DRP-AI Driver
( Optional ) TVM also creates Preprocessing of input images
- Supported Operators
  - Crop
  - Resize
  - Normalization
- Addition parameters
  - input format
  - Tensor Order
  - Type

Sparse Model Translation

The DRP-AI MAC supports sparse arrays (unstructured pruning). The expansion pack includes CLI and python libraries (expansion pack). The expansion pack allows for integration of the Pruning process into the ML Frameworks for training. The Expansion Pack supports Pytorch, Tensorflow, and Tensorflow-lite. This optimization increases the AI Inference performance to 80 TOPS.

Step S1 ) Pruning

The DRP-AI support Structured and Unstructured Pruning
Renesas DRP-AI pruning tool support Tensorflow and Pytorch
Requires full retaining of the model so not to degrade the AI Model accuracy.
Recommend a PC with highend GPU.

Step S2 ) Quantization.

Required for RZ/V2H
Translates a model hyper parameters to INT8.
Requires additional AI Learning. Test Data Set should be sufficient.
Included in the DRP-AI TVM

Step S3 ) Translation

This Auto Tool, ( no special language )
Converts the Standard ML Frameworks Tensorflow, Tensorflow-lite, Pytorch, ONNX, etc. to DRP-AI code
Output is a series of Binary and Configuration files required by the DRP-AI Driver
( Optional ) TVM also creates Pre-processing of input images
- Supported Operators
  - Crop
  - Resize
  - Normalization
- Addition parameters
  - input format
  - Tensor Order
  - Type

RZ/V2N DRP-AI Translator and Quantization Tool

Official Site

This tool is used by the TVM for translation of AI Models. It is needed to install the TVM. ( AI SDK includes this )

For Advance Translation this tool can also be used for AI Model translation instead of the Renesas TVM. Only AI Model operations listed in the RZ\V2H DRP-AI Translator Manual ( section 4.1) can be used with this translator. For AI models that have un-supported operations please use the Renesas DRP-AI TVM Tool. The tool supports quantization and translation of AI Models exported in the ONNX format to the RZ/V2N DRP-AI (INT8) hardware. This tool includes the following

RZ/V2N DRP-AI Translator
DRP-AI Quantization Tool

The RZV2H DRP-AI MAC only performs INT8 operations, so AI Models must be quantized before translation.

Getting Started

The RZV2H AI SDK page is the recommended place to start evaluating the RZ/V2H EVK. The page includes detailed information about setup of the EVK, and of the AI SDK Development Environment. Building a Yocto BSP,. links to Yocto Packages and information is here..

RZ/V2H AI Applications Tutorial Getting Started | Renesas

Setup AI SDK Environment and Evaluate Prebuilt Image

Step 1 Obtain EVK Board
- Links to the AI SDK and EVK
Step 2 Obtain Necessary Environment
- List Software and hardware requirments
Step 3 Obtain the AI SDK
- Download the RZ/V2H AI SDK
- AI SDK Source not needed for initial evaluation
- See Prebuilt Images for more information
Step 4 Setup SDK
Step 5 Build AI Application
- Requires TVM Runtime Library to run applications
  - Instructions steps 5 - 7 show how to get the library from AI SDK
  - TVM Runtime for RZV2H can be found here too.
  - Deploy TVM Runtime to Board
    - Section 2 "Deploy Application to the Board"
- Link to Demo Applications mentioned in this step
  - The link included information on how to build, deploy and run the application
  - More Demos see here.
Step 6 Deploy and Run Applications
- Follow the RZ/V2H EVK Getting Started page

Yocto Build

The Renesas AI SDK includes information about building the AI SDK using the Yocto Build Framework. This is recommended to customize the Linux BSP.

Download the AI SDK Source
Follow the direction "How to build RZ/V2H AI SDK Source Code"

The BSP includes the following packages

RZ/V2H Linux VLP
DRP-AI Drivers
DRP OpenCV Accelerator
Mali Graphics ( Restricted License )
Renesas Codec ( H.265/H.264 ) ( Restricted License )

Not included

Demos ( see here for information )
e-Con MIPI Driver ( see link )
- follow step 5 to install e-CON Camera
Unrestricted Mali Graphics and Codec License
- Request for Unrestricted Graphic Mali License

CM33 and CR7 Multi-OS and FSP

Instructions for RZV Cortex-M33 Multi-OS Package is located below
( Supported on RZV2H AI SDK 2.10 or higher ).

Cortex-M33 Multi-OS Package here wiki

ARM Full Image Signal Processor (ISP)

Image signal processor: ARM: Mali™-C55

RZ/V ISP Wiki here

RZ/V2H ISP Support Package here

Image Processing

OpenCV DRP Acceleration

By default OpenCV is included AI SDK.
OpenCV Version 4.1
DRP Acceleration
- OpenCV DRP Acceleration uses the RZ/V2H DRP ( not DRP-AI ) hardware IP

Note: Open CV DRP Accelerator uses the DRP-AI hardware

Demos

Face Mosaic repo
- Hides person identity by blurring the face.
- AI Model YoloV3 Face Mosaic DRP-AI
- OpenCV

RZ Codec ( H.265 and H.264) and Image Scaling Unit (ISU)

The RZ Codec can be used either as H.264 or H.265.

GSTreamer

GStreamer User's Manual: here
The RZ GStreamer includes plugins for H.264, H.265, and ISU.

OMX Support

Robot Operating System ROS2

RZ/V2H Robotic Operating System ROS 2

ROS2 Wiki page here
RZ/V2H ROS2 Support Package here
RZ/V2H ROS2 Sample Application Package here
ROS2 Repository here

RZ MPU Security Package (Linux OS)

RZ/V2N Security Package here

Hardware

Power Supply

Recommended Power Supplies ( Recommend 100Ws )

	Description	Link	Comments

Description

Link

Comments

🙂

Amazon Basics

Link

2xUSB-C, 2xUSB,

1x65-100W, 1x18W, 2x12W

🙂

Nekteck