CCStudio™ Edge AI Studio

Accelerate Your AI Development on TI Embedded Devices

CCStudio™ Edge AI Studio is a comprehensive suite of graphical and command line tools designed to simplify the development, training, compilation, and deployment of AI models onto Texas Instruments' wide range of processors, microcontrollers, and radar sensors. Whether you are using a model from the TI Model Zoo or bringing your own data and models, CCStudio™ Edge AI Studio provides the tooling you need to get from concept to production faster.

Choose Your Focus Area:
Monitoring and Control - Time Series
Time Series
Implement AI for real-time analysis of time series data. Solutions include arc-fault detection, motor bearing fault detection, and fan blower imbalance fault detection, enabling predictive maintenance with high accuracy on TI Microcontrollers.

Time Series solutions are also available on the cloud.

Perception - Vision
Vision
Develop solutions for object detection, image classification, and semantic segmentation. Leverage scalable processors (AM62A, AM68A, AM69A) for applications in automotive, factory automation, and autonomous mobile robots.
Perception - Radar
Radar
Integrate machine learning with TI mmWave radar sensors for reliable sensing applications. Use cases include surface classification and point cloud classification.
Additional Tools:
Model Analyzer
For vision applications, Model Analyzer allows you to experience first-hand the superior performance of TI's products optimized for Edge AI. It enables the evaluation of accelerated deep learning inference on remotely accessed development boards. Benchmark embedded deep learning inference in under five minutes. Select from hundreds of optimized, trained models or use a custom model. Obtain latency, frames-per-second processing, DDR bandwidth and accuracy benchmarks.
Available remote development boards:
Model Selection Tool
For vision applications, find the model that best meets your performance and accuracy goals on TI Processors from TI Model Zoo. Learn current performance statistics of models such as FPS, Latency, Accuracy & DDR bandwidth.
Model Development Tools for Programmers
Our Texas Instruments GitHub hosts a more extensive and flexible set of model-development tools. Advanced users and developers may prefer these Linux® based PC tools to:
  • Train TI models for a custom dataset (BYOD)
  • Compile a custom or open source model for TI's AI accelerators (BYOM)
  • Analyze and optimize models for performance and accuracy
Microcontroller (MCU) and Microprocessor (MPU) devices will use separate repositories