Developer toolbox supports STM32Cube microcontrollers at the edge

Driving artificial intelligence (AI) to edge and node embedded devices, STMicroelectronics has introduced the STM32 neural network developer toolbox.

AI uses trained artificial neural networks to classify data signals from motion and vibration sensors, environmental sensors, microphones and image sensors, more quickly and efficiently than conventional handcrafted signal processing.

The STM32Cube.AI extension (X-Cube-AI) software tool generates optimised code to run neural networks on STM32 microcontrollers. It can be downloaded inside ST’s STM32CubeMX MCU configuration and software code-generation ecosystem.

Today, the tool supports Caffe, Keras (with TensorFlow backend), Lasagne, ConvnetJS frameworks and integrated development environments (IDEs) including those from Keil, IAR, and System Workbench.

The FP-AI-Sensing1 software function pack provides examples of code to support end-to-end motion (human-activity recognition) and audio (audio-scene classification) applications based on neural networks. This function pack leverages ST’s SensorTile reference board to capture and label the sensor data before the training process. The board can then run inferences of the optimised neural network.

The ST Bluetooth low energy (BLE) Sensor mobile app acts as the SensorTile’s remote control and display.

The toolbox consists of the STM32Cube.AI mapping tool, application software examples running on small form factor, battery-powered SensorTile hardware, together with the partner program and dedicated community support offers a fast and easy path to neural network implementation on STM32 devices.

The extension is supplied with ready-to-use software function packs containing code examples for human activity recognition and audio scene classification that are immediately usable with ST‘s reference sensor board and mobile app.

Developer support is provided through qualified partners in the ST Partner Program and dedicated AI/machine learning (ML) STM32 community, assures the company.

ST explains that STM32Cube.AI can be used by developers to convert pre-trained neural networks into C-code that calls functions in optimised libraries that can run on STM32 microcontrollers.

Accompanying software function packs include example code for human activity recognition and audio scene classification. These code examples are immediately usable with the ST SensorTile reference board and the ST BLE Sensor mobile app.

ST will demonstrate applications developed using STM32Cube.AI running on STM32 microcontrollers in a private suite at CES, the Consumer Electronics Show, in Las Vegas, (8 to 12 January).

http://www.st.com