sahi

SAHI: Slicing Aided Hyper Inference

A lightweight vision library for performing large scale object detection & instance segmentation

​

Overview

Object detection and instance segmentation are by far the most important applications in Computer Vision. However, the detection of small objects and inference on large images still need to be improved in practical usage. Here comes the SAHI to help developers overcome these real-world problems with many vision utilities.

Command	Description
predict	perform sliced/standard video/image prediction using any ultralytics/mmdet/detectron2/huggingface/torchvision model
predict-fiftyone	perform sliced/standard prediction using any ultralytics/mmdet/detectron2/huggingface/torchvision model and explore results in fiftyone app
coco slice	automatically slice COCO annotation and image files
coco fiftyone	explore multiple prediction results on your COCO dataset with fiftyone ui ordered by number of misdetections
coco evaluate	evaluate classwise COCO AP and AR for given predictions and ground truth
coco analyse	calculate and export many error analysis plots
coco yolov5	automatically convert any COCO dataset to ultralytics format

Quick Start Examples

📜 List of publications that cite SAHI (currently 200+)

🏆 List of competition winners that used SAHI

Tutorials

• Introduction to SAHI

• Official paper (ICIP 2022 oral)

• Pretrained weights and ICIP 2022 paper files

• Visualizing and Evaluating SAHI predictions with FiftyOne (2024) (NEW)

• 'Exploring SAHI' Research Article from 'learnopencv.com'

• 'VIDEO TUTORIAL: Slicing Aided Hyper Inference for Small Object Detection - SAHI' (RECOMMENDED)

• Video inference support is live

• Kaggle notebook

• Satellite object detection

• Error analysis plots & evaluation (RECOMMENDED)

• Interactive result visualization and inspection (RECOMMENDED)

• COCO dataset conversion

• Slicing operation notebook

• YOLOX + SAHI demo:

• YOLO11 + SAHI walkthrough: (NEW)

• RT-DETR + SAHI walkthrough: (NEW)

• YOLOv8 + SAHI walkthrough:

• DeepSparse + SAHI walkthrough:

• HuggingFace + SAHI walkthrough:

• YOLOv5 + SAHI walkthrough:

• MMDetection + SAHI walkthrough:

• Detectron2 + SAHI walkthrough:

• TorchVision + SAHI walkthrough:

Installation

Installation details:

• Install sahi using pip:

pip install sahi

• On Windows, Shapely needs to be installed via Conda:

conda install -c conda-forge shapely

• Install your desired version of pytorch and torchvision (cuda 11.3 for detectron2, cuda 11.7 for rest):

conda install pytorch=1.10.2 torchvision=0.11.3 cudatoolkit=11.3 -c pytorch

conda install pytorch=1.13.1 torchvision=0.14.1 pytorch-cuda=11.7 -c pytorch -c nvidia

• Install your desired detection framework (yolov5):

pip install yolov5==7.0.13

• Install your desired detection framework (ultralytics):

pip install ultralytics==8.3.50

• Install your desired detection framework (mmdet):

pip install mim
mim install mmdet==3.0.0

• Install your desired detection framework (detectron2):

pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu113/torch1.10/index.html

• Install your desired detection framework (huggingface):

pip install transformers timm

• Install your desired detection framework (super-gradients):

pip install super-gradients==3.3.1

Framework Agnostic Sliced/Standard Prediction

Find detailed info on sahi predict command at cli.md.

Find detailed info on video inference at video inference tutorial.

Find detailed info on image/dataset slicing utilities at slicing.md.

Error Analysis Plots & Evaluation

Find detailed info at Error Analysis Plots & Evaluation.

Interactive Visualization & Inspection

Find detailed info at Interactive Result Visualization and Inspection.

Other utilities

Find detailed info on COCO utilities (yolov5 conversion, slicing, subsampling, filtering, merging, splitting) at coco.md.

Find detailed info on MOT utilities (ground truth dataset creation, exporting tracker metrics in mot challenge format) at mot.md.

Citation

If you use this package in your work, please cite it as:

@article{akyon2022sahi,
  title={Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection},
  author={Akyon, Fatih Cagatay and Altinuc, Sinan Onur and Temizel, Alptekin},
  journal={2022 IEEE International Conference on Image Processing (ICIP)},
  doi={10.1109/ICIP46576.2022.9897990},
  pages={966-970},
  year={2022}
}

@software{obss2021sahi,
  author       = {Akyon, Fatih Cagatay and Cengiz, Cemil and Altinuc, Sinan Onur and Cavusoglu, Devrim and Sahin, Kadir and Eryuksel, Ogulcan},
  title        = {{SAHI: A lightweight vision library for performing large scale object detection and instance segmentation}},
  month        = nov,
  year         = 2021,
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.5718950},
  url          = {https://doi.org/10.5281/zenodo.5718950}
}

Contributing

sahi library currently supports all Ultralytics (YOLOv8/v10/v11/RTDETR) models, MMDetection models, Detectron2 models, and HuggingFace object detection models. Moreover, it is easy to add new frameworks.

All you need to do is, create a new .py file under sahi/models/ folder and create a new class in that .py file that implements DetectionModel class. You can take the MMDetection wrapper or YOLOv5 wrapper as a reference.

Before opening a PR:

• Install required development packages:

pip install -e ."[dev]"

• Reformat with black and isort:

python -m scripts.run_code_style format

Contributors

Fatih Cagatay Akyon

Sinan Onur Altinuc

Devrim Cavusoglu

Cemil Cengiz

Ogulcan Eryuksel

Kadir Nar

Burak Maden

Pushpak Bhoge

M. Can V.

Christoffer Edlund

Ishwor

Mehmet Ecevit

Kadir Sahin

Wey

Youngjae

Alzbeta Tureckova

So Uchida

Yonghye Kwon

Neville

Janne Mäyrä

Christoffer Edlund

Ilker Manap

Nguyễn Thế An

Wei Ji

Aynur Susuz

Pranav Durai

Lakshay Mehra

Karl-Joan Alesma

Jacob Marks

William Lung

Amogh Dhaliwal