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.
Analysis of switch-mode power supply: inductor violations Altron Arrow
Editor's Choice Power Electronics / Power Management
Common switch-mode power supply (SMPS) design errors are discussed, and their appropriate rectification is specified, with details on complications that arise with the power stage design of DC-DC switching regulators.
Read more...Microsoft Windows IoT on ARM Altron Arrow
Computer/Embedded Technology
This expansion means that the Windows IoT ecosystem can now harness the power of ARM processors, known for their energy efficiency and versatility.
Read more...Microchip introduces ECC608 TrustMANAGER Altron Arrow
Circuit & System Protection
To increase security on IoT products and facilitate easier setup and management, Microchip Technology has added the ECC608 TrustMANAGER with Kudelski IoT keySTREAM, Software as a Service (SaaS) to its Trust Platform portfolio of devices, services and tools.
Read more...SolidRun unveils new SoM Altron Arrow
AI & ML
SolidRun and Hailo has unveiled a game-changer for engineers and AI product developers with the launch of their market-ready SoM, which packs the cutting-edge capabilities of the Hailo-15H SoC.
Read more...An evolutionary step in customisable logic Altron Arrow
DSP, Micros & Memory
Microchip Technology is offering a tailored hardware solution with the launch of its PIC16F13145 family of microcontrollers, which are outfitted with a new Configurable Logic Block module.
Read more...MCU for battery-powered applications Altron Arrow
DSP, Micros & Memory
Included in ST’s family of devices is the STM32U031, an ultra-low-power MCU featuring an ARM Cortex-M0+ 32-bit core running at up to 56 MHz.
Read more...LoRaWAN-certified sub-GHz module Altron Arrow
Telecoms, Datacoms, Wireless, IoT
The STM32WL5M from ST Microelectronics is the company’s first LoRaWAN-certified module which incorporates two cores, one of them being a wireless stack to optimise the creation of sub-GHz applications.
Read more...Dual-port USB-C power delivery solution Altron Arrow
Power Electronics / Power Management
Infineon’s CYPD7272-68LQXQ is the tray packing option of the company’s dual-port USB-C power delivery solution and features an integrated dual-port USB-C PD + DC-DC controller.
printer friendly version