FALCONH8 LANNER | Alldatasheet

Document overview

  • Manufacturer or author: Provided By alldatasheet.com(free datasheet download site)
  • PDF pages: 2

Technical content

Features

  • Best-in-class Performance And Cost-efficiency
  • Scalable, Supports 4, 5 or 6 Hailo-8™ AI Processors
  • High Power Efficiency, Low Power Consumption
  • Commercial and Industrial Grade Support
  • Enablement Software Package with Advanced Deep Learning Models and AI Reference Applications
  • Hailo-8™ Software Development Tools Significantly Reduce the Time to Market of AI Applications AI Performance Up To 156 TOPs 8000 FPS Of ResNet-50, 1300 FPS Of YOLOv5m AI Processors 4-6 Hailo-8™ AI Processors with Hailo Patented Structure Defined Dataflow Architecture AI Frameworks Support Hailo AI Dataflow Compiler With Profiler And Emulator Supports TensorFlow, ONNX And PyTorch Frameworks PCIexpress Interface PCI Express x16 Compliant With PCI Express Specification v3.0 System Compatibility Intel x86 or ARM Devices, Linux OS e.g., Ubuntu, Yocto Lanner Network and Edge AI Appliances Power Consumption Typical: 35W Temperature Operating: 0~70ºC (Commercial Grade) -40~85ºC (Industrial Grade) Storage: -40~85ºC Humidity 5% - 90% RH, Non-condensing Dimension Standard PCIe Single Slot Form-factor 167.65mm x 111.15mm Without Bracket Certifications CE Class A, FCC Class A FALCON-H8 Product Overview Lanner’s Falcon H8 modular, PCIe form factor provides an easily deployable solution for engineers looking to offload CPU loading for low-latency deep learning inference. With high-density AI processors, the Falcon H8 accommodates 4, 5, or 6 Hailo-8™ AI Processors, offering a modular, cost-effective Edge AI solution with high processing capabilities and power efficiency. Through a standard PCIe interface, the Falcon H8 AI Accelerator Card enables legacy devices such as NVRs, Edge AI boxes, Industrial PCs and robots to run video-intensive, mission-critical Edge AI applications such as video analytics, traffic management, access control, and beyond. FALCON-H8A IEK-AI0001A, Commercial Grade, Onboard 6x Hailo-8™ AI Processor FALCON-H8B IEK-AI0001B, Commercial Grade, Onboard 5x Hailo-8™ AI Processor FALCON-H8C IEK-AI0001C, Commercial Grade, Onboard 4x Hailo-8™ AI Processor FALCON-H8D IEK-AI0001D, Industrial Grade, Onboard 6x Hailo-8™ AI Processor FALCON-H8E IEK-AI0001E, Industrial Grade, Onboard 5x Hailo-8™ AI Processor FALCON-H8F IEK-AI0001F, Industrial Grade, Onboard 4x Hailo-8™ AI Processor

Ordering Information

  • NVRs & Edge AI Boxes
  • Industrial Gateways & PCs
  • Industrial Robots

© Lanner Electronics Inc. All rights reserved. All product specifications are subject to change without notice. contact@lannerinc.com | www.lannerinc.com FALCON-H8 V1-2022.04.26 Feature Highlights Hailo Toolchain and Developer Tools FALCON H8 enables scalable, powerful, cost-effective and low power consumption intelligent video analytics (IVA) applications for intelligent transportation, smart cities, smart retail and Industry 4.0 devices

  • Quality control automation
  • Line inspection
  • Predictive maintenance
  • Vision-based inventory trackin
  • Hazard and crime detection
  • Parking laws enforcement
  • Public health Monitoring
  • Traffic law enforcement
  • Traffic flow analytics
  • Automatic number-plate recognition
  • Flow & Queue analysis
  • Smart advertising
  • Customer identification
  • Store inspection The Hailo Dataflow Compiler API seamlessly integrates with existing deep learning development frameworks to allow smooth and easy integration in existing development ecosystems. Hailo Dataflow Compiler is used for compiling users’ models to Hailo binaries. The input of the Dataflow Compiler is a trained Deep Learning model. The output is a binary file which is loaded to the Hailo device. The HailoRT API is used for deploying the built model on the target device. This library is used by the runtime applications. Supported Intelligent Applications High Efficiency Typical Power Consumption 35W Cost-effective Lowest TOPs/$ Ease of HW & SW integration Hailo AI Dataflow Compiler Standard PCIe single slot form-factor Various DL Architectures Hailo Model Zoo Hailo TAPAAS AI Applications Advanced AI Applications Supports state-of-the-art NN model in high resolution High Processing Power Up to 156 TOPS 8000FPS of ResNet-50 Runtime environmentModel build environment ML Frameworks Hailo Dataflow Compiler HailoRT Falcon-H8 Hailo-8™ firmware UserspaceKernel C/C++ API and library OS IP stack PCIe Hailo Model Zoo User’s models App pipeline elements App examples TAPPASUser’s apps Pre-trained models Build & eval tools Re-training env Runtime Frameworks Plugins Tools Integration & CLI Hailo PCIe driverHailo PCIe Driver pyHailoRT (Python API)