Moffet AI’s FPGA Accelerated Visual Search Engine and Service are ready made to accelerate Visual Search inference across a wide variety of industries and applications, such as surveillance, smart retail, content search, social media and autonomous vehicles.
Moffett AI’s approach delivers an order of magnitude higher efficiency via reduced need for OPS & smaller network size (storage), delivering up to 15x lower cost compared to GPU based solutions.
Moffett AI offers a breakthrough Visual Search as a Service (VSaaS) Solution architecture based on Sparse Processing on FPGAs— for Face Identification and Visual Search which is widely used in surveillance, smart retail, social media and autonomous vehicles.
Through software-hardware co-optimization, Moffett AI and Xilinx can offer low-power, low-cost alternative to high-end GPUs for low-latency visual search on huge databases.
- VSaaS Offered on Global Cloud (AWS F1, Alibaba F3 Instance)
- Advanced, Compatible Toolchain & SDK integrates with existing workflows, allows for advanced optimization
- Compatible with ML Frameworks including: Tensor Flow, PyTorch, ONNX frameworks
Contact Moffett AI for access to the Visual Search Amazon Machine Instance for a free 14 day trial: info@moffett.ai
A wide range of development and deployment resources are available from Moffett AI, including:
- White Paper: A visual search engine on Moffett’s Sparse Processing Units
- Solution Brief: Xilinx Accelerated, Cloud Based Sparse Neural Network Accelerated Visual Search
- Video Demo – Moffett AI Visual Search F1 based AMI on Amazon Marketplace
- Visual Search as a Service: Moffett AI Visual Search Engine AMI on AWS Marketplace
- User Guide / SDK User Guide
- Moffett AI Performance Tools for Quantization / Pruning