STMicroelectronics introduces new tools for edge AI development
STMicroelectronics has expanded its edge AI products by introducing the STM32Cube.AI developer cloud. This online development platform aims to accelerate edge computing application development. The solution targets embedded engineers and data scientists, making it easier for them to work with the STM32 family of microcontrollers and bring edge AI technology to market faster. The comprehensive development tools aim to streamline the process of combining hardware and software solutions.
STMicroelectronics’ STM32Cube.AI developer cloud is an online platform that allows users to create optimized code for STM32 microcontrollers. It leverages the company’s STM32Cube.AI technology to offer the ability to optimize and benchmark edge AI models. The online platform also features an ST model zoo, which includes reference models, training scripts and application examples.
The STM32Cube.AI developer cloud platform provides embedded developers access to edge AI use cases, such as human motion sensing for object recognition and tracking and computing vision for image classification. Industry experts believe the STM32 model zoo will ease machine learning project development and reduce the time to market. The pre-trained neural network models for edge computing can be deployed directly on STM32 microcontroller boards, reducing development time and validation.
“Our goal is to deliver the best hardware, software, and services to meet the challenges faced by embedded developers and data scientists so that they can develop their edge AI application faster and with less hassle,” said Ricardo De Sa Earp, executive vice president general-purpose microcontroller sub-group, STMicroelectronics.
STMicroelectronics has been providing edge AI solutions through the STM32Cube.AI desktop front-end, which allows developers to validate and optimize STM32 AI libraries from trained neural networks. When combined with the STM32Cube.AI developer cloud, this provides the ability to evaluate the performance of AI models and select an appropriate hardware architecture.
The central technology behind STM32Cube.AI is a set of tools available for engineers to create and train neural network models using popular frameworks, such as TensorFlow Lite, Keras, qKeras and PyTorch. This tool enables the user to convert pre-trained neural network models into efficient C-code for any STM32 microcontroller board.
“Today, we are unveiling the world’s first MCU AI Developer Cloud, which works hand-in-glove with our STM32Cube.AI ecosystem. This new tool brings the possibility to remotely benchmark models on STM32 hardware through the cloud to save on workload and cost,” Earp further added.
Article Topics
AI/ML | application development | chip | edge AI | microcontroller | model | STMicroelectronics | training
Comments