# meituan/yolov6 **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/meituan-yolov6).** 5,882 stars · 1,062 forks · Jupyter Notebook · GPL-3.0 ## Links - GitHub: https://github.com/meituan/YOLOv6 - awesome-repositories: https://awesome-repositories.com/repository/meituan-yolov6.md ## Topics `object-detection` `pytorch` `yolo` ## Description YOLOv6 is a single-stage deep learning framework designed for industrial object detection. It serves as a computer vision model trainer for identifying and locating objects within images, as well as an instance segmentation tool that delineates precise object boundaries using masks. The project includes a specialized mobile inference optimizer and a model quantization toolkit. These components focus on reducing model size and resolution to improve execution speed on ARM-based chipsets and converting models to low-precision formats to decrease file size. The framework covers a broad range of capabilities, including custom model training, real-time instance segmentation, and model runtime conversion for cross-platform execution. It also supports edge device inference optimization to maintain performance across various hardware runtimes. ## Tags ### Artificial Intelligence & ML - [Object Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/object-detection.md) — Provides a high-performance framework for identifying and locating multiple objects within images using bounding boxes. ([source](https://github.com/meituan/yolov6#readme)) - [Instance Segmentation Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-libraries/instance-segmentation-engines.md) — Implements engines that generate pixel-level masks to isolate individual object instances in real-time. - [Computer Vision Model Trainers](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-model-trainers.md) — Serves as a toolkit for optimizing weights of vision-specific neural networks using custom datasets. - [Object Mask Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/image-segmentation/object-mask-generators.md) — Generates precise pixel-level masks to delineate the boundaries of identified object instances. ([source](https://github.com/meituan/yolov6#readme)) - [Detection Model Training](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-model-training/detection-model-training.md) — Enables training of object detection and instance segmentation models on custom datasets. ([source](https://github.com/meituan/YOLOv6/wiki/FAQ%EF%BC%88Continuously-updated%EF%BC%89)) - [Edge Hardware Optimizations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/training-algorithms/machine-learning-optimization/ml-performance-profilers/hardware-specific-model-optimizations/edge-hardware-optimizations.md) — Applies quantization and graph optimizations to reduce latency and memory footprint on resource-constrained edge devices. - [Model Quantization](https://awesome-repositories.com/f/artificial-intelligence-ml/model-quantization.md) — Provides a toolkit for reducing model weight precision to decrease file size and accelerate inference. ([source](https://github.com/meituan/yolov6#readme)) - [Single-Stage Detectors](https://awesome-repositories.com/f/artificial-intelligence-ml/single-stage-detectors.md) — Employs a neural network architecture that predicts object bounding boxes in a single pass for high throughput. - [Anchor-Free Detection Logic](https://awesome-repositories.com/f/artificial-intelligence-ml/anchor-box-systems/anchor-free-detection-logic.md) — Implements detection architectures that regress object locations directly from center points without predefined bounding box shapes. - [Structural Reparameterizations](https://awesome-repositories.com/f/artificial-intelligence-ml/backpropagation/reparameterization-trick/structural-reparameterizations.md) — Combines multiple training-time network branches into a single streamlined inference layer to reduce latency. - [Inference Model Deployment](https://awesome-repositories.com/f/artificial-intelligence-ml/inference-model-deployment.md) — Converts models from high-level frameworks into optimized compute graphs for cross-platform hardware execution. ([source](https://github.com/meituan/YOLOv6/wiki/FAQ%EF%BC%88Continuously-updated%EF%BC%89)) - [Resolution Scaling](https://awesome-repositories.com/f/artificial-intelligence-ml/inference-scaling/resolution-scaling.md) — Adjusts input image dimensions and layer depth to optimize processing speed and memory usage on ARM processors. - [Inference Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/inference-optimization.md) — Includes a specialized pipeline to reduce model size and resolution for improved execution speed on ARM chipsets. - [Model Quantization Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/serving-and-runtime/model-quantization-tools.md) — Ships a toolkit for converting models to low-precision formats to decrease file size and accelerate inference. - [Quantization-Aware Training](https://awesome-repositories.com/f/artificial-intelligence-ml/model-quantization/quantization-aware-training.md) — Utilizes training techniques that simulate quantization noise to minimize accuracy drops in compressed models. - [C++ Inference Exports](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training/model-exporting/c-inference-exports.md) — Provides functionality to export trained models for C++ runtime deployment to remove Python dependencies. ### Part of an Awesome List - [Object Detection Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/object-detection-frameworks.md) — Provides a comprehensive software toolkit for implementing state-of-the-art object detection for industrial applications. - [Computer Vision](https://awesome-repositories.com/f/awesome-lists/ai/computer-vision.md) — Industrial-grade object detection framework. - [Object Detection Models](https://awesome-repositories.com/f/awesome-lists/ai/object-detection-models.md) — Industrial-grade object detection framework optimized for speed and accuracy. - [CNN](https://awesome-repositories.com/f/awesome-lists/more/cnn.md) — Listed in the “CNN” section of the Ailia Models awesome list. - [Object Detection](https://awesome-repositories.com/f/awesome-lists/more/object-detection.md) — Listed in the “Object Detection” section of the The Incredible Pytorch awesome list. ### Mobile Development - [Mobile Model Deployment](https://awesome-repositories.com/f/mobile-development/mobile-model-deployment.md) — Optimizes model size and resolution specifically for deployment on mobile hardware and ARM-based chipsets. ([source](https://github.com/meituan/yolov6#readme)) ### DevOps & Infrastructure - [Model Conversion](https://awesome-repositories.com/f/devops-infrastructure/model-conversion.md) — Transforms trained models into optimized formats compatible with various inference engines.