STM32CubeAI-DC

概述

样片和购买

Partner products

銷售公文包

开始

Please enter your desired search query and search again

本产品状态为

我们推荐您使用以下产品作为替代:

STEDGEAI-DC

产品概述

描述

STM32Cube.AI Developer Cloud (STM32CubeAI-DC) is a free-of-charge online platform and services to create, optimize, benchmark, and generate artificial intelligence (AI) for the STM32 microcontrollers and microprocessors based on the Arm^® Cortex^® processors. It can leverage AI hardware acceleration (neural processing unit, NPU) whenever available in the target hardware.

STM32CubeAI-DC uses the ST edge AI core technology, which is STMicroelectronics technology to optimize NN models for any STMicroelectronics products with AI capabilities. For STM32 MCUs, its performance is identical to the X-CUBE-AI Expansion Package used with STM32CubeMX. Find STM32Cube.AI Developer Cloud at stm32ai-cs.st.com.

所有功能
Online GUI (no installation required) accessible with STMicroelectronics extranet user credentials

Network optimization and visualization prodiving the RAM and flash memory sizes needed to run on the STM32 target

Quantization tool to convert a floating-point model into an integer model

Benchmark service on the STMicroelectronics hosted board farm including various STM32 boards to make the most suited hardware selection

Code generator including the network C code and optionally the whole STM32 project

STM32 model zoo:

Easy access to model selection, training script, and key model metrics, directly available for benchmark

Application code generator from the user’s model with “Getting started” code examples

ML workflow automation service with Python™ scripts (REST API)

For STM32 MCUs, supports all the X-CUBE-AI features, such as:

Native support for various deep learning frameworks such as Keras and TensorFlow™ Lite, and support for all frameworks that can export to the ONNX standard format such as PyTorch™, MATLAB^®, and more

Support for the 8-bit quantization of Keras networks and TensorFlow™ Lite quantized networks

Support for various built-in scikit-learn models such as isolation forest, support vector machine (SVM), K-means, and more

Possibility to use larger networks by storing weights in external flash memory and activation buffers in external RAM

Easy portability across different STM32 microcontroller series

Supports all STM32 MPU series with the following features:

Native support for various deep learning frameworks such as Keras and TensorFlow™ Lite, and support for all frameworks that can export to the ONNX standard format such as PyTorch™, MATLAB^®, and more

Support for the 8-bit quantization of Keras networks and TensorFlow™ Lite quantized networks

Support for various built-in scikit-learn models such as isolation forest, support vector machine, K-means, and more

CPU inference via TensorFlow™ Lite runtime or ONNX Runtime for the STM32 microprocessors that do not support AI hardware acceleration

NPU/GPU inference processing for the STM32 microprocessors that support AI hardware acceleration

User-friendly license terms
阅读更多阅读较少信息