Overview
Description
Renesas RUHMI (Robust Unified Heterogenous Model Integration) Framework is an AI tool integrating an embedded AI compiler* with e2 studio, generating highly optimized models in minutes to run efficiently on Renesas embedded processors. This AI tool is simple for beginners and powerful for experts.
Why RUHMI Framework?
Robust compiler and software framework for efficient deployment of the latest neural network models in a framework-agnostic manner.
- Enable deep neural network graph compilation and AI inference, with the necessary tools, APIs, code generator, and runtime needed to deploy a pre-trained deep neural network.
- Support Python interfaces for workflow integration and customization
- Native support for ML frameworks and can import models from TensorFlow Lite and ONNX
- Framework-agnostic post-training calibration and quantization of user-defined models
- Simplify deployment by auto-converting to optimized .C or .h source code
- Ready-to-use application examples, including optimized models for cutting-edge RA8P1 MCUs
- Flexible deployment support includes UX-centric GUI for Windows, and CLI for Windows and Linux users.
- User experience-focused design – allowing users to select their model from available frameworks, convert their models, and store weight with either RAM or ROM.
* Powered by EdgeCortix® MERA™ 2.0
Features
- Heterogenous compiler supporting models from different frameworks: TF-Lite & ONNX.
- Post-training quantization
- Graph optimization and partitioning (hardware agnostic)
- Heterogenous code generation with hardware-specific optimizations
- C-code generation for MCU
Release Information
For additional information and links, visit GitHub.
Target Devices
Documentation
|
|
|
---|---|---|
Type | Title | Date |
Quick Start Guide | PDF 1.25 MB | |
Flyer | PDF 493 KB 日本語 | |
2 items
|
Design & Development
Related Boards & Kits
Evaluation Kit for RA8P1 MCU Group
The EK-RA8P1 evaluation kit is designed to enable users to easily evaluate the RA8P1 MCU features and develop embedded system applications using Renesas' Flexible Software Package (FSP) and e2 studio IDE. Users can utilize the rich onboard features and their choice of popular ecosystem add-ons...
Videos & Training
Learn how the Renesas Robust Unified Heterogenous Model Integration (RUHMI) Framework simplifies AI model integration. This tool combines an embedded AI compiler with e2 studio to quickly generate optimized models for Renesas embedded processors, making it ideal for both beginners and experts.
Related Resources