Skip to content

Latest commit

 

History

History
692 lines (482 loc) · 22.5 KB

README.rst

File metadata and controls

692 lines (482 loc) · 22.5 KB
Raw

Hailo TAPPAS - Optimized Execution of Video-Processing Pipelines

./resources/github_Tappas_Mar24.jpg

Gstreamer 1.16 | 1.18 | 1.20 HailoRT License: LGPL v2.1

Overview

TAPPAS is Hailo's set of full application examples, implementing pipeline elements and pre-trained AI tasks.

Demonstrating Hailo's system integration scenario of specific use cases on predefined systems (software and Hardware platforms). It can be used for evaluations, reference code and demos:

  • Accelerating time to market by reducing development time and deployment effort
  • Simplifying integration with Hailo’s runtime SW stack
  • Providing a starting point for customers to fine-tune their applications

Getting Started with Hailo-8

Prerequisites

  • Hailo-8 device
  • HailoRT PCIe driver installed
  • At least 6GB's of free disk space

Note

This version is compatible with HailoRT v4.19.

Installation

Option Instructions Supported OS
Hailo SW Suite* SW Suite Install guide Ubuntu x86 20.04, Ubuntu x86 22.04
Pre-built Docker image Docker install guide Ubuntu x86 20.04, Ubuntu x86 22.04, Ubuntu aarch64 20.04 (64-bit)
Manual install Manual install guide Ubuntu x86 20.04, Ubuntu x86 22.04, Ubuntu aarch64 20.04
Yocto installation Read more about Yocto installation Yocto supported BSP's
Raspberry Pi 4 installation Read more about Raspberry Pi 4 installation Raspberry Pi OS
Raspberry Pi 5 installation Read more about Raspberry Pi 5 installation Raspberry Pi OS

* It is recommended to start your development journey by first installing the Hailo SW Suite

Documentation

Getting Started with Hailo-15

TAPPAS is now released separately for Hailo-8, for Hailo-15 please refer to https://github.com/hailo-ai/tappas/tree/master-vpu.

For a quick start with Hailo-15, please refer to the Vision Processor Software Package documentation section in Hailo's Developer Zone.

Example Applications Built with TAPPAS

Note

For the Raspberry Pi 5 applications, go to Hailo Raspberry Pi 5 Examples.

Note

These example applications are part of the Hailo AI Software Suite.

Hailo offers an additional set of Application Code Examples.

TAPPAS comes with a rich set of pre-configured pipelines optimized for different common hosts.

Important

  • All example applications utilize both the host (for non-neural tasks) and the Neural-Network Core (for neural-networks inference), therefore performance results are affected by the host.
  • General application examples do not include any architecture-specific accelerator usage, and therefore will provide the easiest way to run an application, but with sub-optimal performance.
  • Architecture-specific application examples (i.MX, Raspberry PI, etc.) use platform-specific hardware accelerators and are not compatible with different architectures.

Note

All i.MX example application are validated on i.MX8 and i.MX6 platforms and are compatible with the architectures.

Note

Running application examples requires a direct connection to a monitor.

Basic Single Network Pipelines

Pipelines that run a single network. The diagram below shows the pipeline data-flow.

resources/single_net_pipeline.jpg

The following table details the currently available examples.

  General i.MX8 RPi4 x86 Hardware Accelerated Rockchip
Object Detection check_mark check_mark check_mark   check_mark
Depth Estimation check_mark check_mark check_mark    
Instance segmentation check_mark        
Classification with Python Postprocessing check_mark        
Object Detection Multiple Devices (Century) check_mark     check_mark  
Face Recognition check_mark        

Two Network Pipelines

Examples of basic pipelines running two networks. The cascaded (serial) flow shows two networks running in series. This example pipeline is of the popular configuration where the first network is a detector which finds some Region-of-Interest (ROI) in the input image and the second network processes the cropped ROI (a face-detection-and-landmarking use case of this pipeline is shown at the top of this guide). The pipeline is shown in the following diagram:

resources/cascaded_nets_pipeline.png

  General i.MX8 RPi4 x86 Hardware Accelerated Rockchip
Cascaded - Face Detection & Landmarks check_mark   check_mark    
Cascaded - Person Det & Single Person Pose Estimation check_mark check_mark      
Cascaded - Face Detection & Recognition check_mark        

Multi-Stream Pipelines

docs/resources/one_network_multi_stream.png

  General i.MX8 RPi4 x86 Hardware Accelerated Rockchip
Multi-stream Object Detection check_mark     check_mark check_mark
Multi-stream Multi-Device Object Detection check_mark        

Pipelines for High-Resolution Processing Via Tiling

docs/resources/tiling-example.png

  General i.MX8 RPi4 x86 Hardware Accelerated Rockchip
HD Object Detection check_mark       check_mark

Example Use Case Pipelines

Our LPR reference application demonstrates the use of 3 networks, with a database. The pipeline demonstrates inference based decision making (Vehicle detection) for secondary inference tasks (License plate data extraction). This allows multiple networks to cooperate in the pipeline for reactive behavior.

resources/lpr_pipeline.png

Our Multi-Person Multi-Camera Tracking reference application demonstrates person tracking across multiple streams using RE-ID tracking. The pipeline demonstrates another method for inference based decision making that also connects between different video streams.

resources/re_id_pipeline.png

  General i.MX8 RPi4 x86 Hardware Accelerated Rockchip
LPR check_mark check_mark     check_mark
RE-ID check_mark        

Support

If you need support, please post your question on our Hailo community Forum for assistance.

Contact information is available at hailo.ai.

Changelog

v3.30.0 (October 2024)

v3.29.1 (August 2024)

  • Hailo-8:
    • Updated infrastructure to better support Raspberry Pi 5
    • Added an option to control Yolo (Detection) Hailort post-process parameters via a JSON configuration
    • Semantic segmentation post-process now extracts the argmax tensor using Regular Expressions

v3.29.0 (July 2024)

  • Hailo-15:
    • Updated all Hailo-15 example applications to use the latest API
    • Added a new C++ based example application that demonstrates the use of the Hailo-15 API Link
    • This release is aligned with the Hailo-15 Vision Processor Software Package 2024-07
  • Hailo-8:
  • Fixed various stability issues across apps and platforms

v3.28.1 (May 2024)

  • Added a new property to hailomuxer which allows the sub-frame to be leaky
  • hailooverlay now properly supports Hailo-15 with a new DMABuf sync mechanism
  • hailovideoscale (Hailo-15 Element) now supports the letterbox property

v3.28.0 (April 2024)

  • Tappas was updated in this version, with a revised list of supported platform and apps
  • Added yolov8 (as default) to Detection application examples
  • Fixed various stability issues across apps and platforms
  • This release is aligned to Hailo-15 Vision Processor Software Package 2024-04

v3.27.2 (March 2024)

  • Aligned to Hailo-15 Vision Processor Software Package 2024-01.2
  • Added a new example application - Frontend Update
  • Updated the hailo OSD API
  • Detection application now works with an updated hailonet element
  • Various bugs fixes

v3.27.1 (February 2024)

  • Aligned to Hailo-15 Vision Processor Software Package 2024-01.1
  • Added a new Hailo-15 external host application that saves udp stream to file

v3.27.0 (January 2024)

  • Updated the Hailo-15 applications to use the updated Media Library implementation:
    • Basic Security Camera (streaming)
    • Detection
    • Single Stream OSD (On-Screen Display)
  • Added a folder for external host scripts and added the UDP Stream Display script

Note

TAPPAS supports both Hailo-15 and Hailo-8. Temporarily, in this version, only the following Hailo-8 based example applications are supported:

  • Detection
    • yolov5
    • mobilenet_ssd
  • Multi-Stream Detection
    • Multi-Stream Detection
    • MultiStream Detection with Stream Multiplexer
  • License Plate Recognition

These applications are supported under the general folder (x86-based platforms).

v3.26.2 (December 2023)

  • Aligned to Hailo-15 Vision Processor Software Package 2023-10.2
  • Add grayscale support for Media Library Front-end
  • Various bug fixes for Hailo-15 pipelines

v3.26.1 (November 2023)

  • Aligned to Hailo-15 Vision Processor Software Package 2023-10.1
  • Updated OSD configuration to support new dynamic features and adjust to the updated Media Library implementation
  • Added a script for displaying UDP streams
  • Basic security camera (Media Library implementation) now support 5 outputs

v3.26.0 (October 2023)

  • Added Hailo-15 supported application examples:
    • Detection
    • License Plate Recognition
    • A new Hailo-15 specific example application - Basic Security Camera (streaming)
  • Removed Yolact models support from Instance Segmentation
  • Various bug fixes:
    • Fixed the Detection application on i.MX6 platforms
    • Fixed an issue with Face Recognition which prevented faces to be recognized ins some scenarios
    • Fixed an issue which caused a warning when running some networks

v3.25.0 (July 2023)

  • Improved Yolov5seg post-process performance
  • Updated Yolo networks to use the HailoRT native post-process (selected models)
  • Added "non-blocking mode" and "wait-time" properties to hailoroundrobin element

v3.24.0 (March 2023)

  • Added support for Rockchip RK3588 (validated on Firefly ITX-3588J platform)
  • Video Management System now supports multi-device (Ubuntu 22.04 only)
  • Video Management System (single device) now works on Ubuntu 20.04
  • Added a new model to Instance Segmentation Pipeline:
    • yolov5seg - which has improved performance compared to yolact
  • New applications for i.MX8:
    • Object Detection and Pose Estimation (cascaded)
    • Multi-Stream Detection
  • Added a TAPPAS Graphic User Interface to easily run selected general example applications (preview) on the TAPPAS Docker - to activate it, run tappas-gui
  • Added back yolox_l_leaky to the Century general application
  • Reduced docker size

v3.23.1 (February 2023)

v3.23.0 (December 2022)

v3.22.0 (November 2022)

  • New element hailoimportzmq - provides an entry point for importing metadata exported by hailoexportzmq (HailoObjects) into the pipeline
  • Added Depth Estimation, Object Detection and Classification pipelines for i.MX6 Pipelines
  • Changed the debugging tracers to use an internal tracing mechanism

v3.21.0 (October 2022)

  • New Apps:
  • New elements - hailoexportfile and hailoexportmq which provide an access point in the pipeline to export metadata (HailoObjects)
  • Improved pipeline profiling by adding new tracers and replacing the GUI of gst-shark
  • Ubuntu 22 is now supported (GStreamer 1.20, preview)
  • Yocto Kirkstone is now supported (GStreamer 1.20)

v3.20.0 (August 2022)

  • New Apps:
  • Improvements to Multi-Camera Multi-Person Tracking (RE-ID) pipeline (released)

v3.19.1 (July 2022)

v3.19.0 (June 2022)

  • New Apps:
    • Added Cascading networks, Depth Estimation, Pose Estimation and Semantic Segmentation pipelines for i.MX Pipelines
  • Added an option to control post-process parameters via a JSON configuration for the detection application
  • Added support for Raspberry Pi Raspbian OS
  • Native Application now uses TAPPAS post-process
  • LPR (License Plate Recognition) pipeline is simplified to bash only
  • New detection post-process - Nanodet

Note

Ubuntu 18.04 will be deprecated in TAPPAS future version

Note

Python 3.6 will be deprecated in TAPPAS future version

v3.18.0 (April 2022)

  • New Apps:
    • LPR (License Plate Recognition) pipeline and facial landmark pipeline for i.MX Pipelines
  • Added the ability of compiling a specific TAPPAS target (post-processes, elements)
  • Improved the performance of Raspberry Pi example applications

v3.17.0 (March 2022)

  • New Apps:
    • LPR (License Plate Recognition) pipeline for General Pipelines (preview)
    • Detection & pose estimation app
    • Detection (MobilenetSSD) - Multi scale tiling app
  • Update infrastructure to use new HailoRT installation packages
  • Code is now publicly available on Github

v3.16.0 (March 2022)

  • New Apps:
    • Hailo Century app - Demonstrates detection on one video file source over 6 different Hailo-8 devices
    • Python app - A classification app using a post-process written in Python
  • New Elements:
    • Tracking element "HailoTracker" - Add tracking capabilities
    • Python element "HailoPyFilter" - Enables to write post-processes using Python
  • Yocto Hardknott is now supported
  • Raspberry Pi 4 Ubuntu dedicated apps
  • HailoCropper cropping bug fixes
  • HailoCropper now accepts cropping method as a shared object (.so)

v3.14.1 (March 2022)

  • Fix Yocto Gatesgarth compilation issue
  • Added support for hosts without X-Video adapter

v3.15.0 (February 2022)

  • New Apps:
    • Detection and depth estimation - Networks switch app
    • Detection (MobilenetSSD) - Single scale tilling app

v3.14.0 (January 2022)

  • New Apps:
    • Cascading apps - Face detection and then facial landmarking
  • New Yocto layer - Meta-hailo-tappas
  • Window enlargement is now supported
  • Added the ability to run on multiple devices
  • Improved latency on Multi-device RTSP app

v3.13.0 (November 2021)

  • Context switch networks in multi-stream apps are now supported
  • New Apps:
    • Yolact - Instance segmentation
    • FastDepth - Depth estimation
    • Two networks in parallel on the same device - FastDepth + Mobilenet SSD
    • Retinaface
  • Control Element Integration - Displaying device stats inside a GStreamer pipeline (Power, Temperature)
  • New Yocto recipes - Compiling our GStreamer plugins is now available as a Yocto recipe
  • Added a C++ detection example (native C++ example for writing an app, without GStreamer)

v3.12.0 (October 2021)

  • Detection app - MobilenetSSD added
  • NVR multi-stream multi device app (detection and pose estimation)
  • Facial Landmarks app
  • Segmentation app
  • Classification app
  • Face detection app
  • Hailomuxer gstreamer element
  • Postprocess implementations for various networks
  • GStreamer infrastructure improvements
  • Added ARM architecture support and documentation

v3.11.0 (September 2021)

  • GStreamer based initial release
  • NVR multi-stream detection app
  • Detection app
  • Hailofilter gstreamer element
  • Pose Estimation app