Overview
Description
The Renesas AI Model Deployer is an intuitive graphical user interface (GUI) tool integrated with NVIDIA’s powerful TAO Toolkit. Removing traditional barriers for embedded developers, whether you're just starting your AI journey or looking to optimize your edge deployment, this approach offers a streamlined, scalable path forward.
The Renesas AI Model Deployer is designed to run locally on standard workstations, making it convenient for developers to prototype and test without needing cloud-based infrastructure. The GUI supports three end-to-end vision pipelines enabling customers to understand how to leverage TAO for object detection and image classification use cases.
The Renesas AI Model Deployer is a practical, end-to-end tool designed specifically for embedded developers who need a straightforward way to manage vision AI workflows. Users can set up the environment quickly by executing self-contained shell scripts, and the GUI offers a complete end-to-end AI development pipeline:
- Project creation (model, board, and task selection)
- Dataset split and analysis
- Model training and optimization (QAT and pruning)
- Visual evaluation (mAP or Top-K accuracy)
- Sample-based inference testing
- Streamlined deployment to hardware
The GUI also supports live camera inference, USB streaming, and intuitive deployment screens, giving developers immediate feedback—and confidence that their models are functioning in real-world scenarios. By wrapping cutting-edge AI techniques into a click-driven experience, Renesas empowers customers to build smarter, more efficient edge products—faster, easier, and with significantly reduced risk.
For those looking to create production-grade systems, the provided Jupyter notebooks via GitHub open up further flexibility. Developers can extend pipelines with custom data curation workflows, explore additional TAO Toolkit features such as sophisticated augmentation strategies, advanced hyperparameter tuning, or even implement Bring Your Own Model (BYOM) approaches. These notebooks turn the foundation provided by the GUI into a fully customizable toolkit ready for real-world applications.
Features
- Technical Integration Examples: Renesas AI Model Deployer supports several hands-on integration examples that showcase real-world AI deployments.
- Object Detection with DetectNet v2 on RZ/V2H and RZ/V2L
- Model: DetectNet v2 with ResNet-18 backbone
- Dataset: KITTI dataset (cars, pedestrians, cyclists)
- Deployment: Quantized models deployed through DRP-AI, featuring live camera inference and bounding box visualization.
- Image Classification with MobileNetV2 on RA8D1 MCU
- Model: MobileNetV2
- Dataset: Biodegradable medical waste classification (10 classes, e.g., syringes, gloves, pipettes)
- Deployment: Quantization via TFLite and deployment through e2 studio.
- Object Detection with DetectNet v2 on RZ/V2H and RZ/V2L
- In addition to these ready-to-use examples, Jupyter notebooks allow developers to experiment beyond the basics. Examples include integrating additional datasets, advanced model retraining, and even leveraging Bring Your Own Model (BYOM) flows for fully customized solutions.
Release Information
For additional information and links, visit GitHub.
Target Devices
Documentation
|
|
|
---|---|---|
Type | Title | Date |
Quick Start Guide | PDF 1.79 MB | |
1 item
|
Design & Development
Related Boards & Kits
RZ/V2H Quad-core Vision AI MPU Evaluation Kit
The RZ/V2H AI MPU evaluation kit (RTK0EF0168C04000BJ) is used to evaluate Renesas' RZ/V2H quad-core vision AI MPU. The kit includes a CPU board and an expansion (EXP) board. It supports RZ/V2H standard software packages and enables easy implementation of software development tasks such as low...
SMARC SOM Evaluation Kit for RZ/V2L MPU with AI Accelerator
The RZ/V2L Evaluation Board Kit consists of a module board (SOM) and a carrier board that can easily start evaluation of the RZ/V2L. It also includes the MIPI Camera Module (MIPI CSI). The carrier board can be commonly used with RZ/G2L, RZ/G2LC, RZ/G2UL, and RZ/V2L modules (SOM) prepared...
Test this Board Remotely
Evaluation Kit for RA8D1 MCU Group
The EK-RA8D1 evaluation kit enables users to effortlessly evaluate the features of the RA8D1 MCU Group and develop embedded systems applications using Renesas' Flexible Software Package (FSP) and e2 studio IDE. Utilize rich onboard features along with your choice of popular ecosystem add-ons to...
AI Kit Development Platform with RA8D1
The AIK-RA8D1 provides developers with multiple and reconfigurable connectivity functions to expedite AI/ML system development. This easy-to-use hardware platform for multimodal AI/ML solutions is based on the RA8D1 MCU from the RA family of 32-bit MCUs.
The hardware platform is intended for use...