Hailo’s TAPPAS (Template APPlications And Solutions) is an infrastructure designed to make it easy to develop and deploy high-performance edge AI applications based on the industry-leading Hailo-8™ AI processor. Hailo TAPPAS is pre-packaged with a rich set of applications built on top of state-of-the-art deep neural network processing, demonstrating Hailo’s best-in-class throughput and power efficiency. For users seeking to quickly deploy their own networks on the Hailo-8, the TAPPAS provides an easy-to-use, Python-based template for application development.
TAPPAS pre-trained applications and development environment reduce development time and effort, allowing customers to accelerate time to market. The open applications infrastructure offers different operational modes, as well as bring-your-own-model and DIY support functionalities that help achieve development flexibility.
TAPPAS object detection app: a high-resolution video feed of a busy speedway processed on the theHailo-8™ AI Processor in real time and with high accuracy of detection.
TAPPAS out-of-the-box versatile apps include:
Ready-made ResNet-50-based application, trained on ImageNet
A ResNet18-UNET-based application, rudimentary in intelligent ADAS cameras
Out-of-the-box PolyLaneNet-based application trained on Tusimple for basic assisted driving applications
Purpose-built and pre-trained model, optimized for high-resolution ,real-time applications like ADAS front-facing cameras
Multiple Object Tracking
An advanced versatile model that detects and tracks multiple simultaneously-moving people
Facial Detection & Recognition
Apps for face recognition and detection app for security and authentication applications
CenterPose-based app for a variety of safety, security and operational optimization applications across verticals
Detection apps with several available neural networks, delivering unique functionalities
A YOLACT-based model that identifies, outlines and colors different objects and persons