Merge pull request #54 from hailo-ai/update-to-version-2.7

update-to-version-2.7.0

CITATION.cff

@@ -0,0 +1,38 @@
+# This CITATION.cff file was generated with cffinit.
+# Visit https://bit.ly/cffinit to generate yours today!
+
+cff-version: 1.2.0
+title: Hailo Model Zoo
+message: >-
+  If you use Hailo in your research, please cite this
+  repository using these metadata.
+type: software
+authors:
+  - given-names: Tamir
+    family-names: Tapuhi
+    email: [email protected]
+  - given-names: Shachar
+    family-names: Gluska
+    email: [email protected]
+  - given-names: Amit
+    family-names: Klinger
+    email: [email protected]
+  - given-names: Nadiv
+    family-names: Dharan
+    email: [email protected]
+  - given-names: Omer
+    family-names: Sholev
+    email: [email protected]
+  - given-names: Yuval
+    family-names: Zelig
+    email: [email protected]
+  - given-names: Niv
+    family-names: Vosco
+    email: [email protected]
+repository-code: 'https://github.com/hailo-ai/hailo_model_zoo'
+url: 'https://hailo.ai/products/hailo-software-suite/model-zoo/'
+abstract: >-
+  The Hailo Model Zoo includes pre-trained models and a full
+  building and evaluation environment
+license: MIT
+date-released: '2021-07-01'

README.rst

@@ -1,45 +1,51 @@
 Hailo Model Zoo
 ===============
 
-.. |python| image:: https://img.shields.io/badge/python-3.8-blue.svg
+.. |python| image:: https://img.shields.io/badge/python-3.8%20%7C%203.9%20%7C%203.10-blue.svg
    :target: https://www.python.org/downloads/release/python-380/
    :alt: Python 3.8
-   :width: 70
+   :width: 150
+   :height: 20
 
 
 .. |tensorflow| image:: https://img.shields.io/badge/Tensorflow-2.9.2-blue.svg
    :target: https://github.com/tensorflow/tensorflow/releases/tag/v2.9.2
-   :alt: Generic badge
-   :width: 90
+   :alt: Tensorflow
+   :width: 110
+   :height: 20
 
 
 .. |cuda| image:: https://img.shields.io/badge/CUDA-11.2-blue.svg
    :target: https://developer.nvidia.com/cuda-toolkit
-   :alt: Generic badge
-   :width: 70
+   :alt: Cuda
+   :width: 80
+   :height: 20
 
 
-.. |compiler| image:: https://img.shields.io/badge/HailoDataflow;Compiler-3.22.1-<COLOR>.svg
+.. |compiler| image:: https://img.shields.io/badge/Hailo%20Dataflow%20Compiler-3.23.0-brightgreen.svg
    :target: https://hailo.ai/contact-us/
-   :alt: Generic badge
+   :alt: Hailo Dataflow Compiler
    :width: 180
+   :height: 20
 
 
-.. |badge| image:: https://img.shields.io/badge/(optional)HailoRT-4.12.1-<COLOR>.svg
+.. |runtime| image:: https://img.shields.io/badge/HailoRT%20(optional)-4.13.0-brightgreen.svg
    :target: https://hailo.ai/contact-us/
-   :alt: Generic badge
-   :width: 100
+   :alt: HailoRT
+   :width: 170
+   :height: 20
 
 
 .. |license| image:: https://img.shields.io/badge/License-MIT-yellow.svg
    :target: https://github.com/hailo-ai/hailo_model_zoo/blob/master/LICENSE
    :alt: License: MIT
-   :width: 70
+   :width: 80
+   :height: 20
 
 
 .. image:: docs/images/logo.png
 
-|python| |tensorflow| |cuda| |compiler| |badge| |license|
+|python| |tensorflow| |cuda| |compiler| |runtime| |license|
 
 
 The Hailo Model Zoo provides pre-trained models for high-performance deep learning applications. Using the Hailo Model Zoo you can measure the full precision accuracy of each model, the quantized accuracy using the Hailo Emulator and measure the accuracy on the Hailo-8 device. Finally, you will be able to generate the Hailo Executable Format (HEF) binary file to speed-up development and generate high quality applications accelerated with Hailo-8. The Hailo Model Zoo also provides re-training instructions to train the models on custom datasets and models that were trained for specific use-cases on internal datasets.
@@ -127,4 +133,4 @@ Please visit `hailo.ai <https://hailo.ai/>`_ for support / requests / issues.
 Changelog
 ---------
 
-For further information please see our `CHANGLOGE <docs/CHANGELOG.rst>`_ page.
+For further information please see our `CHANGELOG <docs/CHANGELOG.rst>`_ page.

docs/CHANGELOG.rst

@@ -1,33 +1,55 @@
 Changelog
 =========
 
+**v2.7**
+
+* Update to use Dataflow Compiler v3.23.0 (`developer-zone <https://hailo.ai/developer-zone/>`_)
+* Updated to use HailoRT 4.13.0 (`developer-zone <https://hailo.ai/developer-zone/>`_)
+* Inference flow was moved to new high-level APIs
+* New object detection variants:
+
+  * yolov8: yolov8n / yolov8s / yolov8m / yolov8l / yolov8x
+  * damoyolo: damoyolo_tinynasL20_T / damoyolo_tinynasL25_S / damoyolo_tinynasL35_M
+
+* New transformers based models:
+
+  * vit_base - classification model
+  * yolov5s_c3tr - object detection model with a self-attention block
+
+* Examples for using HailoRT-pp - support for seamless integration of models and their corresponding postprocessing
+
+  * yolov5m_hpp
+
+* Configuration YAMLs and model-scripts for networks with YUY2 input format
+* DAMO-YOLO retraining docker
+* Bug fixes
+
 **v2.6.1**
 
 * Bug fixes
-* Update to use Dataflow Compiler v3.22.1 (`developer-zone <https://hailo.ai/developer-zone/>`_)
-* Updated to use HailoRT 4.12.1 (`developer-zone <https://hailo.ai/developer-zone/>`_)
 
 **v2.6**
 
 * Update to use Dataflow Compiler v3.22.0 (`developer-zone <https://hailo.ai/developer-zone/>`_)
 * Updated to use HailoRT 4.12.0 (`developer-zone <https://hailo.ai/developer-zone/>`_)
-* ViT (`Vision Transformer <https://arxiv.org/pdf/2010.11929.pdf>`_) - new classification network with transformers-encoder based architecture 
+* ViT (`Vision Transformer <https://arxiv.org/pdf/2010.11929.pdf>`_) - new classification network with transformers-encoder based architecture
 * New instance segmentation variants:
 
   * yolov5n_seg
   * yolov5s_seg
   * yolov5m_seg
-
+  * yolov5l_seg
+
 * New object detecion variants for high resolution images:
 
   * yolov7e6
   * yolov5n6_6.1
   * yolov5s6_6.1
   * yolov5m6_6.1
-  
+
 * New flag ``--performance`` to reproduce highest performance for a subset of networks
 * Hailo model-zoo log is now written into ``sdk_virtualenv/etc/hailo/modelzoo/hailo_examples.log``
-* Bug fixes 
+* Bug fixes
 
 **v2.5**
 
@@ -37,8 +59,8 @@ Changelog
 
   * yolact_regnetx_800mf
   * yolact_regnetx_1.6gf
-  
-* Bug fixes 
+
+* Bug fixes
 
 **v2.4**
 
@@ -48,8 +70,8 @@ Changelog
 * New models:
 
   * Face Detection - scrfd_500m / scrfd_2.5g / scrfd_10g
-  
-* New tasks: 
+
+* New tasks:
 
   1. Super-Resolution
 
@@ -64,7 +86,7 @@ Changelog
       #. arcface_mobilefacenet
     * Retraining docker for arcface architecture
 
-* Added support for new hw-arch - hailo8l 
+* Added support for new hw-arch - hailo8l
 
 **v2.3**
 
@@ -75,7 +97,7 @@ Changelog
   * yolov7 / yolov7-tiny
   * nanodet_repvgg_a1_640
   * efficientdet_lite0 / efficientdet_lite1 / efficientdet_lite2
-  
+
 * New tasks:
 
   * mspn_regnetx_800mf - single person pose estimation
@@ -94,13 +116,13 @@ Changelog
   * Hailo model zoo data directory by default will be ``~/.hailomz``
 
 * New models:
-  
+
   * yolov5xs_wo_spp_nms - a model which contains bbox decoding and confidence thresholding on Hailo-8
   * osnet_x1_0 - person ReID network
   * yolov5m_6.1 - yolov5m network from the latest tag of the repo (6.1) including silu activation
 
 * New tasks:
-  
+
   * person_attr_resnet_v1_18 - person attribute recognition
 
 * ReID training docker for the Hailo model repvgg_a0_person_reid_512/2048
@@ -121,7 +143,7 @@ Changelog
   * | repvgg_a0_person_reid_512 / repvgg_a0_person_reid_2048 - ReID networks which outputs a person embedding
     | These models were trained in-house as part of our upcoming new application
   * | stdc1 - Segmentation architecture for Cityscapes
-      
+
 **v2.0**
 
 * Updated to use Dataflow Compiler v3.16 (`developer-zone <https://hailo.ai/developer-zone/>`_) with TF version 2.5 which require CUDA11.2
@@ -144,7 +166,7 @@ Changelog
 
 * Added new documentation to the `YAML structure <YAML.rst>`_
 
-   
+
 **v1.5**
 
 * Remove HailoRT installation dependency.
@@ -173,7 +195,7 @@ Changelog
 
   * | hand_landmark_lite from MediaPipe
   * | palm_detection_lite from MediaPipe
-  
+
   | Both tasks are without evaluation module.
 
 
@@ -221,7 +243,7 @@ Changelog
 * Model Optimization API Changes
 
   * Model Optimization parameters can be updated using the networks' model script files (\*.alls)
-  
+
   * Deprecated: quantization params in YAMLs
 
 * Training Guide: new training guide for yolov5 with compatible Dockerfile
@@ -261,25 +283,25 @@ Changelog
 
 **v1.1**
 
-* Support VisDrone Dataset 
-* New task: pose estimation 
+* Support VisDrone Dataset
+* New task: pose estimation
 
-  * centerpose_regnetx_200mf_fpn 
-  * centerpose_regnetx_800mf 
-  * centerpose_regnetx_1.6gf_fpn 
+  * centerpose_regnetx_200mf_fpn
+  * centerpose_regnetx_800mf
+  * centerpose_regnetx_1.6gf_fpn
 
-* New task: face detection 
+* New task: face detection
 
-  * lightfaceslim 
-  * retinaface_mobilenet_v1 
+  * lightfaceslim
+  * retinaface_mobilenet_v1
 
-* New models: 
+* New models:
 
-  * hardnet39ds 
-  * hardnet68 
-  * yolox_tiny_leaky 
-  * yolox_s_leaky 
-  * deeplab_v3_mobilenet_v2 
+  * hardnet39ds
+  * hardnet68
+  * yolox_tiny_leaky
+  * yolox_s_leaky
+  * deeplab_v3_mobilenet_v2
 
 * Use your own network manual for YOLOv3, YOLOv4_leaky and YOLOv5.
 

docs/GETTING_STARTED.rst

@@ -9,8 +9,8 @@ System Requirements
 
 * Ubuntu 20.04/22.04, 64 bit (supported also on Windows, under WSL2)
 * Python 3.8/3.9/3.10, including ``pip`` and ``virtualenv``
-* Hailo Dataflow Compiler v3.22.1 (Obtain from `hailo.ai <http://hailo.ai>`_\ )
-* HailoRT 4.12.1 (Obtain from `hailo.ai <http://hailo.ai>`_\ ) - required only for inference on Hailo-8.
+* Hailo Dataflow Compiler v3.23.0 (Obtain from `hailo.ai <http://hailo.ai>`_\ )
+* HailoRT 4.13.0 (Obtain from `hailo.ai <http://hailo.ai>`_\ ) - required only for inference on Hailo-8.
 * The Hailo Model Zoo supports Hailo-8 connected via PCIe only.
 * Nvidia’s Pascal/Turing/Ampere GPU architecture (such as Titan X Pascal, GTX 1080 Ti, RTX 2080 Ti, or RTX A4000)
 * GPU driver version 470

docs/HAILO_MODELS.rst

@@ -7,6 +7,7 @@ Each model is accompanied with its own README, retraining docker and retraining
 
 
 * FLOPs in the table are counted as MAC operations.
+* All models were compiled using Hailo Dataflow Compiler v3.23.0
 * Supported tasks:
 
   * `Object Detection`_