EDGE-AI-STUDIO
面向边缘 AI 的软件开发工具
EDGE-AI-STUDIO
概述
Edge AI Studio 是旨在加速 TI 处理器、微控制器和雷达传感器上边缘 AI 开发的一系列图形和命令行工具。无论是使用 TI Model Zoo 中的模型开发概念验证,
还是利用您自己的模型,Edge AI Studio 都能提供所需的工具。
Edge AI Studio 图形用户界面提供了完整的集成解决方案,用于数据收集和标注、模型训练和编译,以便在实时开发平台上部署。从 TI Model Zoo 中的各种预训练模型中进行选择,并可选择使用自定义数据重新训练,以提高准确性和性能。Edge AI Studio 可作为处理器设备提供基于云的应用程序,为微控制器提供云和桌面两种应用程序。使用微控制器时,Edge AI Studio 的输出可用于 Code Composer Studio™ 开发环境。
对于高级用户或使用 PyTorch、TensorFlow 等开源环境的用户,TI 提供了一套命令行工具,可在这些环境中使用 TI 器件。Tensor Virtual Machine (TVM) 编译器框架用于优化 TI 器件的模型,无论器件是否配备专用加速器均可使用。在使用具有专用 AI 加速器(例如 C7x/MMA)的 TI 处理器 (MPU) 时,TI 深度学习库 (TIDL) 包含经高度优化的常见层实现,以确保提供卓越性能。借助命令行工具,还可以实现
自定义模型 (BYOM) 的使用。
特性
TI 支持多种应用的边缘 AI 解决方案开发,包括但不限于:
处理器 (MPU)
- 目标检测
- 图像分类
- 语义分段
微控制器 (MCU)
- 电弧故障检测
- 电机故障检测
- 鼓风机不平衡
- 通用时间序列
雷达传感器
- 表面分类
下载
EDGE-AI-STUDIO — Edge AI Studio
支持的产品和硬件
产品
多媒体和工业网络 SoC
汽车驾驶辅助 SoC
硬件开发
评估板
EDGE-AI-STUDIO — Edge AI Studio
产品
多媒体和工业网络 SoC
汽车驾驶辅助 SoC
硬件开发
评估板
发布信息
Model Composer is a fully integrated no-code solution for training and compiling models for deployment into edge AI applications. It supports Bring-Your-Own-Data (BYOD), enabling the re-training of models from the TI Model Zoo with custom data. Deploy to your local development board.
Tasks supported:
- Image classification
- Object detection
- Semantic segmentation
- AC/DC Arc fault detection
- Passive Infra Red (PIR) classification for CC27xx
- Motor bearing fault detection
- Blower Imbalance detection
- Time-series Classification task support for C2000, MSPM0, CC27xx
- Surface Classification for mmWave
- Point Cloud Classification task support for mmWave
新增功能
- Arc Fault Task supports AC arc fault use case on MSPM0
- Passive Infra Red (PIR) classification for CC27xx
- Time-series Classification task support for C2000, MSPM0, CC27xx
- Point Cloud Classification task support for mmWave
- Project create workflow improvements.
EDGE-AI-STUDIO-MCU — Edge AI Studio for Microcontrollers
支持的产品和硬件
产品
Sub-1GHz 无线 MCU
Wi-Fi 产品
低功耗 2.4GHz 产品
实时数字电源 MCU
实时电机控制和自动化 MCU
汽车动力总成、区域与机箱控制 MCU
汽车车身和照明 MCU
通用 MCU
硬件开发
子卡
开发套件
评估板
EDGE-AI-STUDIO-MCU — Edge AI Studio for Microcontrollers
产品
Sub-1GHz 无线 MCU
Wi-Fi 产品
低功耗 2.4GHz 产品
实时数字电源 MCU
实时电机控制和自动化 MCU
汽车动力总成、区域与机箱控制 MCU
汽车车身和照明 MCU
通用 MCU
硬件开发
子卡
开发套件
评估板
发布信息
Edge AI Studio is part of the CCStudio™ development tool ecosystem. Edge AI Studio is a collection of graphical and command line tools designed to accelerate edge AI development on TI processors, microcontrollers, connectivity devices and radar sensors. It supports both AI-accelerated devices such as processors featuring a C7™ NPU or microcontrollers featuring a TinyEngine™ as well as AI-supported devices without a dedicated accelerator.
The Edge AI Studio graphical user interface provides a fully integrated solution for data management, model training and deployment on a live development platform. Select from a variety of optimized pre-trained models in the TI Model Zoo and optionally re-train them with custom data (BYOD) to improve accuracy and performance.
Features
- TI Model Zoo containing a wide variety of optimized models
- Supports tasks and models across Time Series, Vision, and Radar
- Supports devices across processors, microcontrollers, connectivity devices and radar sensors
- Data collection
- Data annotation
- Model training with custom data (BYOD)
- Deploy to a live device
- Integration with CCStudio™ IDE
新增功能
- Introduce additional Time-series AI tasks
- Regression and Forecasting
- Enable core AI support across TI's MCU device families
- Enabled for all AI accelerated devices and other non-accelerated devices
- Expand core AI support to AM13, AM26, CC13xx, CC27xx, CC35xx, C28xx, C29xx, MSPM0, MSPM33
- Add Sensor BoosterPack™ support for data collection, live preview across MCU LaunchPads™
- Accelerometer + gyroscope, PIR, microphone, ambient light, humidity and temperature
- Enable Library of example projects with predefined datasets
- Enhanced user experience (Revamped workspace, new project, training and deployment workflows)