hailo_model_zoo - Hailo Model Zoo v2.16

v2.16

Update to use Dataflow Compiler v3.32.0 (developer-zone)
Update to use HailoRT 4.22.0 (developer-zone)
Removed support for hailo15h, hailo15m, hailo15l and hailo10h
Removed support for clipvitl14 and clipvitl14_laion2B models
Bug fixes

- Python
Published by HailoModelZoo 6 months ago

hailo_model_zoo - Hailo Model Zoo v5.0

v5.0

Update to use Dataflow Compiler v5.0.0 (developer-zone)
Update to use HailoRT v5.0.0 (developer-zone)
New Models:
SigLip - SigLip2-base-32 - Contrastive Language-Image Pre-training model
Bug fixes

- Python
Published by HailoModelZoo 8 months ago

hailo_model_zoo - Hailo Model Zoo v2.16

v2.16

Update to use Dataflow Compiler v3.32.0 (developer-zone)
Update to use HailoRT 4.22.0 (developer-zone)
Removed support for hailo15h, hailo15m, hailo15l and hailo10h
Removed support for clipvitl14 and clipvitl14_laion2B models
Bug fixes

- Python
Published by HailoModelZoo 8 months ago

hailo_model_zoo - Hailo Model Zoo v2.15

v2.15

Update to use Dataflow Compiler v3.31.0 (developer-zone <https://hailo.ai/developer-zone/>_)
Update to use HailoRT 4.21.0 (developer-zone <https://hailo.ai/developer-zone/>_)
New Models:
- CLIP <https://arxiv.org/pdf/2103.00020>_ - ViT-Base-16, ViT-Base-32, ViT-Large-14 (336x336 resolution) - Contrastive Language-Image Pre-training model [Hailo-15H and Hailo-10H only]
- Real-ESRGAN <https://arxiv.org/pdf/2107.10833>_ - x4 - Super Resolution model [Hailo-15H and Hailo-10H only]
- PoolFormer <https://arxiv.org/pdf/2111.11418>_ - s12 - Vision Transformer classification model [Hailo-15M/H and Hailo-10H only]
Bug fixes

- Python
Published by HailoModelZoo 11 months ago

hailo_model_zoo - Hailo Model Zoo v2.12

Changelog

v2.12

Update to use Dataflow Compiler v3.28.0 (developer-zone <https://hailo.ai/developer-zone/>_)
Update to use HailoRT 4.18.0 (developer-zone <https://hailo.ai/developer-zone/>_)
Target hardware now supports Hailo-10H device
New Models:
- Original ViT models - tiny, small, base - Transformer based classification models
- DeiT models - tiny, small, base - Transformer based classification models
- DETR (resnet50) - Transformer based object detection model
- fastvit_sa12 - Fast transformer based classification model
- levit256 - Transformer based classification model
- YOLOv10 - nano, small - Latest YOLO detectors
- RepGhostNet1.0x, RepGhostNet2.0x - Hardware-Efficient classification models
New postprocessing support on NN Core:
- yolov6 tag 0.2.1
Added support for person attribute visualization
Bug fixes

- Python
Published by HailoModelZoo over 1 year ago

hailo_model_zoo - Hailo Model Zoo v2.11

Changelog

v2.11

Update to use Dataflow Compiler v3.27.0 (developer-zone <https://hailo.ai/developer-zone/>_)
Update to use HailoRT 4.17.0 (developer-zone <https://hailo.ai/developer-zone/>_)
New Models:
- FastSAM-s - Zero-shot Instance Segmentation
- Yolov9c - Latest Object Detection model of the YOLO family
Using HailoRT-pp for postprocessing of the following variants:
- nanodet

Postprocessing JSON configurations are now part of the cfg directory.

Introduced new flags for hailomz CLI:
- --start-node-names and --end-node-names for customizing parsing behavior.
- --classes for adjusting the number of classes in post-processing configuration.

The --performance flag, previously utilized for compiling models with their enhanced model script if available, now offers an additional functionality. In instances where a model lacks an optimized model script, this flag triggers the compiler's Performance Mode to achieve the best performance

These flags simplify the process of compiling models generated from our retrain dockers.

Bug fixes

- Python
Published by HailoModelZoo almost 2 years ago

hailo_model_zoo - Hailo Model Zoo v2.10

v2.10

Update to use Dataflow Compiler v3.26.0 (developer-zone)
Update to use HailoRT 4.16.0 (developer-zone)
Using HailoRT-pp for postprocessing of the following variants:
- yolov8
Porfiler change:
- Removal of --mode flag from hailomz profile command, which generates a report according to provided HAR state.
CLI change:
- hailo8 target is deprecated in favor of hardware
Support KITTI Stereo Dataset
New Models:
- vitposesmall - encoder based transformer with layernorm for pose estimation
- segformerb0bn - encoder based transformer with batchnorm for semantic segmentation
Bug fixes

- Python
Published by HailoModelZoo about 2 years ago

hailo_model_zoo - hotfix to v2.9

added KITTI Stereo dataset and fixed a few broken links

- Python
Published by HailoModelZoo over 2 years ago

hailo_model_zoo - Hailo Model Zoo v2.9

Update to use Dataflow Compiler v3.25.0 (developer-zone <https://hailo.ai/developer-zone/>_)
Update to use HailoRT 4.15.0 (developer-zone <https://hailo.ai/developer-zone/>_)
A new CLI-compatible API that allows users to incorporate format conversion and reshaping capabilities into the input:
code-block:

hailomz compile yolov5s --resize 1080 1920 --input-conversion nv12torgb
New transformer models added:
- vitposesmall_bn - encoder based transformer with batchnorm for pose estimation
- clipresnet50x4 - Contrastive Language-Image Pre-Training for zero-shot classification
New retraining dockers for vit variants using unified normalization.
New Models:
- yolov8spose / yolov8mpose - pose estimation
- scdepthv3 - depth-estimation
- dncnn3 / dncnncolorblind - image denoising
- zerodcepp - low-light enhancement
- stereonet - stereo depth estimation

-Using HailoRT-pp for postprocessing of the following models:

efficientdetlite0 / efficientdetlite1 / efficientdet_lite

- Python
Published by HailoModelZoo over 2 years ago

hailo_model_zoo - Hailo Model Zoo v2.8

Update to use Dataflow Compiler v3.24.0 (developer-zone)
Update to use HailoRT 4.14.0 (developer-zone)
The Hailo Model Zoo now supports the following vision transformers models:
- vittiny / vitsmall / vit_base - encoder based transformer with batchnorm for classification
- detrresnetv118bn - encoder/decoder transformer for object detection
- clipresnet50 - Contrastive Language-Image Pre-Training for zero-shot classification
- yolov5s_c3tr - object detection model with a MHSA block
Using HailoRT-pp for postprocessing of the following variants:
- yolov5
- yolox
- ssd
- efficientdet
- yolov7
New Models:
- repvgga1 / repvgga2 - classification
- yolov8seg: yolov8nseg / yolov8sseg / yolov8mseg - instance segmentation
- yolov6n_0.2.1 - object detection
- zero_dce - low-light enhancement
New retraining dockers for:
- yolov8
- yolov8_seg
Enable compilation for hailo15h device
Enable evaluation of models with RGBX / NV12 input format
Bug fixes

- Python
Published by HailoModelZoo over 2 years ago

hailo_model_zoo - Hailo Model Zoo v2.7

Update to use Dataflow Compiler v3.23.0 (developer-zone)
Updated to use HailoRT 4.13.0 (developer-zone)
Inference flow was moved to new high-level APIs
New object detection variants:
- yolov8: yolov8n / yolov8s / yolov8m / yolov8l / yolov8x
- damoyolo: damoyolotinynasL20T / damoyolotinynasL25S / damoyolotinynasL35M
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

- Python
Published by HailoModelZoo almost 3 years ago

hailo_model_zoo - Hailo Model Zoo v2.6

Update to use Dataflow Compiler v3.22.0
Updated to use HailoRT 4.12.0
ViT (Vision Transformer) - new classification network with transformers-encoder based architecture
New instance segmentation variants:
- yolov5n_seg
- yolov5s_seg
- yolov5m_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 sdkvirtualenv/etc/hailo/modelzoo/hailoexamples.log
Bug fixes

- Python
Published by HailoModelZoo about 3 years ago

hailo_model_zoo - Hailo Model Zoo v2.5

Update to use Dataflow Compiler v3.20.1 (developer-zone)
Model scripts use new bgr to rgb conversion
New Yolact variants - with all COCO classes:
- yolactregnetx800mf
- yolactregnetx1.6gf
Bug fixes

- Python
Published by HailoModelZoo over 3 years ago

hailo_model_zoo - Hailo Model Zoo v2.4

Updated to use Dataflow Compiler v3.20 (developer-zone)
Required FPS was moved from models YAML into the models scripts
Model scripts use new change activation syntax
New models:
- Face Detection - scrfd500m / scrfd2.5g / scrfd_10g
New tasks:
- Super-Resolution
  - Added support for BSD100 dataset
  - The following models were added: espcnx2 / espcnx3 / espcn_x4
- Face Recognition
  - Support for LFW dataset
  - The following models were added:
    - arcface_r50
    - arcface_mobilefacenet
  - Retraining docker for arcface architecture
Added support for new hw-arch - hailo8l