工具

The neural network models provided in the model zoo are optimized for various applications on the ST target devices.

Monitor data acquisition and track live data on the user interface.

Customize widgets for accurate data source management and visualization.

Line charts of MEMS sensor data.

Load, analyze, and evaluate models from Keras, ONNX, and TFLite on the intelligent sensor processing unit (ISPU).

Collect data, generate decision trees, and configure sensors with a machine learning core (MLC).

Use the automatic filtering and feature selection for a simpler MLC configuration process.

NanoEdge AI Studio selects the best ML algorithm for a given microcontroller (low code / no code solution).

Supports all STM32 microcontrollers, more than 100 ST development boards, 20 Arduino boards, and over 1,000 Arm^® Cortex^®-M microcontrollers.

No expertize required. Create tiny, state-of-the-art AI models for microcontrollers in record time.

NanoEdgeAI Studio offers a unique and patented approach that enables on-device learning directly on the microcontroller.

Use the online tool to streamline the development of AI-enabled IoT nodes.

Quickly create decision tree algorithms running on the machine learning core embedded in MEMS sensors.

Discover proof-of-concepts using ST reference designs.

NanoEdge AI Studio selects the best ML algorithm for a given microcontroller (low code / no code solution).

No expertize required. Create tiny, state-of-the-art AI models for microcontrollers in record time.

Supports all STM32 microcontrollers, more than 100 ST development boards, 20 Arduino boards, and over 1,000 Arm^® Cortex^®-M microcontrollers.

NanoEdgeAI Studio offers a unique and patented approach that enables on-device learning directly on the microcontroller.

Start with your own dataset or select an existing dataset.

The training process on ST or on custom datasets shows the related accuracy/loss charts and confusion matrix.

A collection of code examples for the most common computer vision applications.

Line charts of MEMS sensor data.

Load, analyze, and evaluate models from Keras, ONNX, and TFLite on the intelligent sensor processing unit (ISPU).

Collect data, generate decision trees, and configure sensors with a machine learning core (MLC).

Use the automatic filtering and feature selection for a simpler MLC configuration process.

Example of the installer.

Evaluate AI model performance in the cloud based on ST devices.

Execute ST Edge AI Core technology to optimize your AI model and get insights into the model execution and performance on ST devices.

Access the ST board farm and enjoy real-time access to physical ST products remotely. Review the performance of your AI models for the selected devices.

Explore the GUI interface with Keras model generation.

Use the IDE panel with validation and performance output.

Generate pretrained neural networks and convert them into efficient Ansi C libraries, which can be easily compiled, installed, and executed on Stellar E MCUs.

Integration of AI plug-in with the Stellar E development environment.

Import your own neural network models into STM32CubeMX, select optimization options, and generate the optimized C code corresponding to the input models.

X-CUBE-AI analyzes the NN model and generates a profiling report that details the NN memory requirements and the inference time, both for the complete network and for each layer.

Evaluate AI model performance in the cloud based on ST devices.

Execute ST Edge AI Core technology to optimize your AI model and get insights into the model execution and performance on ST devices.

Access the ST board farm and enjoy real-time access to physical ST products remotely. Review the performance of your AI models for the selected devices.

The neural network models provided in the model zoo are optimized for various applications on the ST target devices.

A collection of code examples for the most common computer vision applications.

Start with your own dataset or select an existing dataset.

The training process on ST or on custom datasets shows the related accuracy/loss charts and confusion matrix.

Line charts of MEMS sensor data.

Load, analyze, and evaluate models from Keras, ONNX, and TFLite on the intelligent sensor processing unit (ISPU).

Collect data, generate decision trees, and configure sensors with a machine learning core (MLC).

Use the automatic filtering and feature selection for a simpler MLC configuration process.

NanoEdge AI Studio selects the best ML algorithm for a given microcontroller (low code / no code solution).

No expertize required. Create tiny, state-of-the-art AI models for microcontrollers in record time.

Supports all STM32 microcontrollers, more than 100 ST development boards, 20 Arduino boards, and over 1,000 Arm^® Cortex^®-M microcontrollers.

NanoEdgeAI Studio offers a unique and patented approach that enables on-device learning directly on the microcontroller.

Example of the installer.

Evaluate AI model performance in the cloud based on ST devices.

Execute ST Edge AI Core technology to optimize your AI model and get insights into the model execution and performance on ST devices.

Access the ST board farm and enjoy real-time access to physical ST products remotely. Review the performance of your AI models for the selected devices.

The neural network models provided in the model zoo are optimized for various applications on the ST target devices.

Explore the GUI interface with Keras model generation.

Use the IDE panel with validation and performance output.

Generate pretrained neural networks and convert them into efficient Ansi C libraries, which can be easily compiled, installed, and executed on Stellar E MCUs.

Integration of AI plug-in with the Stellar E development environment.

Import your own neural network models into STM32CubeMX, select optimization options, and generate the optimized C code corresponding to the input models.

X-CUBE-AI analyzes the NN model and generates a profiling report that details the NN memory requirements and the inference time, both for the complete network and for each layer.