open-mmlab/mmyolo

📄 Table of Contents

• 🥳 🚀 What's New
  • ✨ Highlight
• 📖 Introduction
• 🛠️ Installation
• 👨‍🏫 Tutorial
• 📊 Overview of Benchmark and Model Zoo
• ❓ FAQ
• 🙌 Contributing
• 🤝 Acknowledgement
• 🖊️ Citation
• 🎫 License
• 🏗️ Projects in OpenMMLab

🥳 🚀 What's New 🔝

💎 v0.6.0 was released on 15/8/2023:

• Support YOLOv5 instance segmentation
• Support YOLOX-Pose based on MMPose
• Add 15 minutes instance segmentation tutorial.
• YOLOv5 supports using mask annotation to optimize bbox
• Add Multi-scale training and testing docs

For release history and update details, please refer to changelog.

✨ Highlight 🔝

We are excited to announce our latest work on real-time object recognition tasks, RTMDet, a family of fully convolutional single-stage detectors. RTMDet not only achieves the best parameter-accuracy trade-off on object detection from tiny to extra-large model sizes but also obtains new state-of-the-art performance on instance segmentation and rotated object detection tasks. Details can be found in the technical report. Pre-trained models are here.

Task	Dataset	AP	FPS(TRT FP16 BS1 3090)
Object Detection	COCO	52.8	322
Instance Segmentation	COCO	44.6	188
Rotated Object Detection	DOTA	78.9(single-scale)/81.3(multi-scale)	121

MMYOLO currently implements the object detection and rotated object detection algorithm, but it has a significant training acceleration compared to the MMDeteciton version. The training speed is 2.6 times faster than the previous version.

📖 Introduction 🔝

MMYOLO is an open source toolbox for YOLO series algorithms based on PyTorch and MMDetection. It is a part of the OpenMMLab project.

The master branch works with PyTorch 1.6+.

Major features

• 🕹️ Unified and convenient benchmark

  MMYOLO unifies the implementation of modules in various YOLO algorithms and provides a unified benchmark. Users can compare and analyze in a fair and convenient way.

• 📚 Rich and detailed documentation

  MMYOLO provides rich documentation for getting started, model deployment, advanced usages, and algorithm analysis, making it easy for users at different levels to get started and make extensions quickly.

• 🧩 Modular Design

  MMYOLO decomposes the framework into different components where users can easily customize a model by combining different modules with various training and testing strategies.

The figure above is contributed by RangeKing@GitHub, thank you very much!

And the figure of P6 model is in model_design.md.

🛠️ Installation 🔝

MMYOLO relies on PyTorch, MMCV, MMEngine, and MMDetection. Below are quick steps for installation. Please refer to the Install Guide for more detailed instructions.

conda create -n mmyolo python=3.8 pytorch==1.10.1 torchvision==0.11.2 cudatoolkit=11.3 -c pytorch -y
conda activate mmyolo
pip install openmim
mim install "mmengine>=0.6.0"
mim install "mmcv>=2.0.0rc4,<2.1.0"
mim install "mmdet>=3.0.0,<4.0.0"
git clone https://github.com/open-mmlab/mmyolo.git
cd mmyolo
# Install albumentations
pip install -r requirements/albu.txt
# Install MMYOLO
mim install -v -e .

👨‍🏫 Tutorial 🔝

MMYOLO is based on MMDetection and adopts the same code structure and design approach. To get better use of this, please read MMDetection Overview for the first understanding of MMDetection.

The usage of MMYOLO is almost identical to MMDetection and all tutorials are straightforward to use, you can also learn about MMDetection User Guide and Advanced Guide.

For different parts from MMDetection, we have also prepared user guides and advanced guides, please read our documentation.

Get Started

• Overview
• Dependencies
• Installation
• 15 minutes object detection
• 15 minutes rotated object detection
• 15 minutes instance segmentation
• Resources summary

Recommended Topics

• How to contribute code to MMYOLO
• Training testing tricks
• MMYOLO model design
• Algorithm principles and implementation
• Replace the backbone network
• MMYOLO model complexity analysis
• Annotation-to-deployment workflow for custom dataset
• Visualization
• Model deployment
• Troubleshooting steps
• MMYOLO application examples
• MM series repo essential basics
• Dataset preparation and description

Common Usage

• Resume training
• Enabling and disabling SyncBatchNorm
• Enabling AMP
• Multi-scale training and testing
• TTA Related Notes
• Add plugins to the backbone network
• Freeze layers
• Output model predictions
• Set random seed
• Module combination
• Cross-library calls using mim
• Apply multiple Necks
• Specify specific device training or inference
• Single and multi-channel application examples

Useful Tools

• Browse coco json
• Browse dataset
• Print config
• Dataset analysis
• Optimize anchors
• Extract subcoco
• Visualization scheduler
• Dataset converters
• Download dataset
• Log analysis
• Model converters

Basic Tutorials

• Learn about configs with YOLOv5
• Data flow
• Rotated detection
• Custom Installation
• Common Warning Notes
• FAQ

Advanced Tutorials

• MMYOLO cross-library application

Descriptions

• Changelog
• Compatibility
• Conventions
• Code Style

📊 Overview of Benchmark and Model Zoo 🔝

Results and models are available in the model zoo.

Supported Tasks

• Object detection
• Rotated object detection

Supported Algorithms

• YOLOv5
• YOLOv5u (Inference only)
• YOLOX
• RTMDet
• RTMDet-Rotated
• YOLOv6
• YOLOv7
• PPYOLOE
• YOLOv8

Supported Datasets

• COCO Dataset
• VOC Dataset
• CrowdHuman Dataset
• DOTA 1.0 Dataset

Module Components

Backbones	Necks	Loss	Common
YOLOv5CSPDarknet YOLOv8CSPDarknet YOLOXCSPDarknet EfficientRep CSPNeXt YOLOv7Backbone PPYOLOECSPResNet mmdet backbone mmcls backbone timm	YOLOv5PAFPN YOLOv8PAFPN YOLOv6RepPAFPN YOLOXPAFPN CSPNeXtPAFPN YOLOv7PAFPN PPYOLOECSPPAFPN	IoULoss mmdet loss

❓ FAQ 🔝

Please refer to the FAQ for frequently asked questions.

🙌 Contributing 🔝

We appreciate all contributions to improving MMYOLO. Ongoing projects can be found in our GitHub Projects. Welcome community users to participate in these projects. Please refer to CONTRIBUTING.md for the contributing guideline.

🤝 Acknowledgement 🔝

MMYOLO is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedback. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to re-implement existing methods and develop their own new detectors.

🖊️ Citation 🔝

If you find this project useful in your research, please consider citing:

@misc{mmyolo2022,
    title={{MMYOLO: OpenMMLab YOLO} series toolbox and benchmark},
    author={MMYOLO Contributors},
    howpublished = {\url{https://github.com/open-mmlab/mmyolo}},
    year={2022}
}

🎫 License 🔝

This project is released under the GPL 3.0 license.

🏗️ Projects in OpenMMLab 🔝

• MMEngine: OpenMMLab foundational library for training deep learning models.
• MMCV: OpenMMLab foundational library for computer vision.
• MMPreTrain: OpenMMLab pre-training toolbox and benchmark.
• MMagic: OpenMMLab Advanced, Generative and Intelligent Creation toolbox.
• MMDetection: OpenMMLab detection toolbox and benchmark.
• MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
• MMRotate: OpenMMLab rotated object detection toolbox and benchmark.
• MMYOLO: OpenMMLab YOLO series toolbox and benchmark.
• MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
• MMOCR: OpenMMLab text detection, recognition, and understanding toolbox.
• MMPose: OpenMMLab pose estimation toolbox and benchmark.
• MMHuman3D: OpenMMLab 3D human parametric model toolbox and benchmark.
• MMSelfSup: OpenMMLab self-supervised learning toolbox and benchmark.
• MMRazor: OpenMMLab model compression toolbox and benchmark.
• MMFewShot: OpenMMLab fewshot learning toolbox and benchmark.
• MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
• MMTracking: OpenMMLab video perception toolbox and benchmark.
• MMFlow: OpenMMLab optical flow toolbox and benchmark.
• MMEditing: OpenMMLab image and video editing toolbox.
• MMGeneration: OpenMMLab image and video generative models toolbox.
• MMDeploy: OpenMMLab model deployment framework.
• MIM: MIM installs OpenMMLab packages.
• MMEval: OpenMMLab machine learning evaluation library.
• Playground: A central hub for gathering and showcasing amazing projects built upon OpenMMLab.