Skip to content

Releases: hailo-ai/tappas

v3.30.0

30 Sep 16:09
Compare
Choose a tag to compare

v3.29.1

31 Jul 10:31
Compare
Choose a tag to compare

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

25 Jul 07:44
Compare
Choose a tag to compare

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
  • This release is aligned with the Hailo-15 Vision Processor Software Package 2024-07

Hailo-8:

  • Added a new example application which demonstrates x86 hardware-accelerated
  • Various bug fixes and stability improvements for Raspberry Pi 5
  • Fixed various stability issues across apps and platforms

v3.28.1

23 May 09:34
Compare
Choose a tag to compare
v3.28.1

v3.28.0

28 Mar 16:22
Compare
Choose a tag to compare

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

v3.26.0

13 Nov 14:27
Compare
Choose a tag to compare

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

13 Nov 14:25
Compare
Choose a tag to compare

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

30 Mar 18:59
Compare
Choose a tag to compare

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

15 Mar 12:57
Compare
Choose a tag to compare

v3.23.1 (February 2023)

  • Updated to HailoRT 4.12.1
  • Fixed a documentation mistake in Writing your own Python postprocess

v3.23.0

15 Mar 12:54
Compare
Choose a tag to compare

v3.23.0 (December 2022)

  • New Apps:
    • Added x86_hw_accelerated example pipelines that use Video Acceleration API (VA-API) over Intel processors that support Quick Sync:
      • Video Management System - a pipeline that demonstrates a VMS application which runs several streams and different tasks - Face Recognition, Face Attributes and Person Attributes. Currently this example pipeline is supported on Ubuntu 22.04 only
      • Multi-stream detection
      • Century
    • Pose Estimation pipeline with two cascading networks - Person detection and single person pose estimation
    • Face recognition
    • Updated i.MX6 Object Detection App - New network, updated the pipeline to include i.MX6 hardware acceleration
  • Added new models to Instance Segmentation Pipeline:
    • yolact_regnetx_1.6gf
    • yolact_regnetx_800mf (80 classes)
  • Century app now uses a new network (yolov5m)
  • Multi-Camera Multi-Person Tracking (RE-ID) - Improved pipeline performance and accuracy
  • Added support for Ubuntu 22.04 (release-grade)