Significant upgrades have been rolled out to Microchip Technology’s VectorBlox Accelerator software development kit (SDK) for convolutional neural network (CNN)-based artificial intelligence/machine learning (AI/ML) inference with PolarFire FPGAs. Along with the recent release of version 1.3 comes 19 new tutorials, bringing the total to 37. These include licence plate recognition in TensorFlow, MobileNet v1 and v2 in TensorFlow and TensorFlow2, various ResNet and SqueezeNet models in ONNX, torchvision ResNet in PyTorch and TinyYoloV4 in TensorFlow.
Network sizes have been reduced by 50% by optimising containers for weights and the built-in bit accuracy simulator’s speed has been tripled compared to version 1.2. Other dependencies that have been upgraded in the SDK include OpenVINO version 2021.4.1 and Python version 4.5.5.62. Microchip also upgraded the Libero software example project and programming file to support Libero software version 2021.2 and hot-swappable camera and HDMI inputs.
The company also added a new application notes section in GitHub that covers the following topics:
• Training custom Yolo V2/V3 networks via DarkNet.
• Running custom Yolo V2/V3 networks.
• Inspecting and converting TensorFlow 2 models.
• Face recognition: summary of the demo design.
• Face recognition: changing the faces database to identify other faces.
Powered by VectorBlox Accelerator SDK version 1.3, PolarFire FPGAs offer two to three times more power-efficient inference in mid-range FPGAs. This enables ML inference in applications that are thermally constrained and operates on battery power in environments that are susceptible to single-event upsets such as those experienced in low-orbit aerospace.
NXP has expanded its MCX A Series Altron Arrow
AI & ML
NXP has significantly expanded its MCX A Series of Arm Cortex-M33 microcontrollers, doubling the portfolio with six new families aimed at industrial and IoT edge applications.
Read more...Quad-Apollo MxFE reference design
Design Automation
The Quad-Apollo MxFE reference design exemplifies a complete, high-performance platform for every-element direct-RF sampling digital beamforming using Analog Devices’ Apollo mixed-signal front-end technology.
Read more...Exploring Bluetooth Channel Sounding Altron Arrow
Telecoms, Datacoms, Wireless, IoT
NXP has enabled BCS on the MCX W72 multi-protocol wireless MCU, which supports Bluetooth Low Energy 6.0, Thread, Zigbee, and Matter.
Read more...Dual-band Wi-Fi 6 companion module Altron Arrow
Telecoms, Datacoms, Wireless, IoT
The SimpleLink Wi-Fi CC33xx family of devices from Texas Instruments are dual-band Wi-Fi 6 companion modules enabling engineers to connect more applications with confidence.
Read more...High-performance linear regulator Altron Arrow
Power Electronics / Power Management
The TI TPS7A57-Q1 is an automotive-grade, high-performance low-dropout linear regulator, engineered for precision power delivery in noise-sensitive systems.
Read more...Quad RF ADC/DAC for wideband transceiver design Altron Arrow
DSP, Micros & Memory
The AD9084 from Analog Devices integrates a quad 16-bit RF digital-to-analogue converter with a maximum sampling rate of 28 GSPS and a quad 12-bit RF analogue-to-digital converter.
Read more...MIKROE signs multi-year deal with Renesas Dizzy Enterprises
Design Automation
MIKROE has signed a multi-year MCU development tool support deal with Renesas, which commits MIKROE to providing development tools for 500 of Renesas’ most popular MCUs.
Read more...Collaboration to explore 10BASE-T1S SPE Altron Arrow
Telecoms, Datacoms, Wireless, IoT
The collaboration between Microchip and Hyundai aims to evaluate and promote the adoption of advanced in-vehicle network technologies leveraging each company’s strengths.
While every effort has been made to ensure the accuracy of the information contained herein, the publisher and its agents cannot be held responsible for any errors contained, or any loss incurred as a result. Articles published do not necessarily reflect the views of the publishers. The editor reserves the right to alter or cut copy. Articles submitted are deemed to have been cleared for publication. Advertisements and company contact details are published as provided by the advertiser. Technews Publishing (Pty) Ltd cannot be held responsible for the accuracy or veracity of supplied material.
printer friendly version