FPGA designer Flex Logic is has launched a platform of machine learning (ML) frameworks for its edge AI inference accelerator chip.
This is part of an increasing trend for FPGA and AI accelerator makers to provide trained ML frameworks that run on the hardware.
The EasyVision Platforms from Flex Logic are designed to help designers get to market quickly with edge computer vision products for a wide range of markets such as robotic vision, industrial, security, and retail analytics.
EasyVision uses the InferX edge AI accelerator chip developed by Flex Logic that combines a 2×2 array of reconfigurable tensor processors and FPGA fabric with ready-to-use models. These have already been trained to perform the most common object detection capabilities such as hard-hat detection, people counting, face mask detection and license plate recognition, reducing the development time for projects.
The platform is currently available as a complete solution that includes a server, accelerator card, and all the software needed to do the object detection but EasyVision also plans to offer it as standalone accelerator cards. It showed such a card with the InferX chip last year (above).
The platforms are based on Dell and HPE computing hardware and include a USB Camera for quick and easy trials and production deployments. A set of initial trained models including models for hardhat detection, people counting and others, are provided with the EasyVision platform. The AI vision model library will be continually refreshed over time in response to customer requirements.
- Low power reference design for edge AI and video processing
- Lattice launches its own AI models for its FPGAs
- Lattice snaps up its AI software provider
“There is an explosive demand today for edge vision solutions that bring AI capabilities to a wide range of products of services – yet many companies lack the expertise or data science know-how to develop and train models and then integrate them with existing AI accelerators,” said Dana McCarty, Vice President of Sales and Marketing for Flex Logix’s Inference Products. “With EasyVision, we are essentially providing an AI/ML ‘platform in a box’ that has the AI model already trained and ready to integrate into an existing application and it’s also been fine tuned to work with a hardware accelerator that is fast and accurate.”
“Flex Logix’s EasyVision solution provides a turnkey solution, converting our data to a trained and quantized model, that met our throughput and accuracy requirements,” said Jack Duan, CTO and co-founder of Emerging Risk Analytics (ERA). “We are able to quickly build an AI inference solution with low-power-consumption requirement that avoids the GPU-caused thermal headaches we’ve been struggling with.”
Other articles on eeNews Europe
- UK blocks Chinese takeover of Welsh graphene maker
- Fujitsu teams for 6G chips and trials
- Metamaterial for 6G mmwave beam-steering antenna
- First room-temperature quantum computer in supercomputing centre
- CEA-Leti, Intel develop self assembly die-to-wafer technique
- The drivers behind Intel’s Scottish software deal