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.
Accelerate development of AI-enabled embedded systems
Design Automation
ADI’s CodeFusion Studio (CFS) is a modern embedded software development platform aimed at accelerating the creation of AI-enabled embedded systems.
Read more...EMC limits and levels Altron Arrow
Editor's Choice Circuit & System Protection
As soon as electronics and electrical systems started interfering with each other, the world had to come to some consensus. Considering physics is universal and does not care about what country electrical/electronic products are used in, it should be the same everywhere, right? It is nearly there, but not quite.
Read more...Introducing STM32CubeMX2 Altron Arrow
Design Automation
STMicroelectronics has launched STM32CubeMX2, a new evolution of its popular configuration and code generation tool for STM32 microcontrollers.
Read more...Next-gen SPE Altron Arrow
Telecoms, Datacoms, Wireless, IoT
Next-generation 100/1000BASE-T1 Single Pair Ethernet PHYs integrate MACsec security, time sensitive networking, and functional safety.
Read more...Industrial vibration sensing simplified Altron Arrow
Analogue, Mixed Signal, LSI
The IIS3DWBG1 from STMicroelectronics is a high performance, three-axis digital vibration sensor engineered for demanding industrial applications where accurate motion monitoring is essential.
Read more...AI assistant for STM32 developers
Design Automation
The STMicroelectronics STM32 Sidekick is an AI-driven assistant fully integrated into the STM32 ecosystem designed to streamline embedded development using STM32 microcontrollers.
Read more...Cost-effective microcontroller series Altron Arrow
DSP, Micros & Memory
The STM32C5 series from STMicroelectronics delivers an excellent balance of performance, efficiency, and affordability for embedded designs that require more capability without increasing bill of materials cost.
Read more...Understanding two key tools for cleaner serial data Altron Arrow
Editor's Choice Analogue, Mixed Signal, LSI
Understanding how pre-emphasis and equalisation works, and when to use one over the other, is critical when designing reliable high-speed systems.
Read more...Next-gen robotic systems initiative EBV Electrolink
Design Automation
EBV Elektronik recently introduced MOVE – Driving Robotics Forward, a new initiative designed by EBV Elektronik‘s Embedded Solutions team to support the development of next-generation robotic systems.
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