# wongkinyiu/yolov7

**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/wongkinyiu-yolov7).**

14,110 stars · 4,361 forks · Jupyter Notebook · GPL-3.0

## Links

- GitHub: https://github.com/WongKinYiu/yolov7
- awesome-repositories: https://awesome-repositories.com/repository/wongkinyiu-yolov7.md

## Topics

`darknet` `pytorch` `scaled-yolov4` `yolor` `yolov3` `yolov4` `yolov7`

## Description

YOLOv7 is a PyTorch vision library and real-time inference engine designed for object detection, human pose estimation, and instance segmentation. It provides a framework for detecting and locating multiple objects within images or video streams using neural networks.

The system includes tools for custom model training and fine-tuning, allowing pre-trained weights to be adapted to specialized datasets via transfer learning. It also supports model weight export and format conversion to facilitate deployment on production servers and embedded edge devices.

## Tags

### Artificial Intelligence & ML

- [Real-Time Object Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/real-time-object-detection.md) — Identifies and locates multiple items within images or video streams using high-performance neural networks in real-time. ([source](https://github.com/wongkinyiu/yolov7#readme))
- [Pose Estimation Models](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations/computer-vision-models/pose-estimation-models.md) — Provides a vision model that identifies keypoints on the human body to determine orientation and posture.
- [Instance Segmentation Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-libraries/instance-segmentation-engines.md) — Generates precise pixel-level masks to distinguish individual object instances within complex visual scenes. ([source](https://github.com/wongkinyiu/yolov7#readme))
- [Computer Vision Libraries](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/development-orchestration-tools/computer-vision-libraries.md) — Provides a collection of model weights and training scripts built on PyTorch for high-performance image analysis.
- [Object Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/object-detection.md) — Builds object detection models using custom datasets and multi-GPU acceleration to recognize specific classes. ([source](https://github.com/wongkinyiu/yolov7#readme))
- [Real-Time](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/inference-runtimes/real-time.md) — Offers a framework optimized for low-latency detection and deployment to production environments.
- [Model Fine-Tuning](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-fine-tuning.md) — Adapts pre-trained weights to specific custom datasets using transfer learning techniques. ([source](https://github.com/wongkinyiu/yolov7#readme))
- [Vision Model Training](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/training-frameworks/model-training-frameworks/vision-model-training.md) — Provides a framework for training neural networks on specialized datasets for visual recognition tasks.
- [Pose Estimation](https://awesome-repositories.com/f/artificial-intelligence-ml/pose-estimation.md) — Detects key body points to analyze posture and orientation for motion tracking or gesture recognition. ([source](https://github.com/wongkinyiu/yolov7#readme))
- [Feature Map Aggregators](https://awesome-repositories.com/f/artificial-intelligence-ml/feature-extraction/convolutional-feature-extractors/feature-map-aggregators.md) — Uses a network block design to merge feature maps and refine spatial information via repeated concatenation.
- [Multi-Scale Feature Pyramids](https://awesome-repositories.com/f/artificial-intelligence-ml/inference-scaling/resolution-scaling/hierarchical-feature-pyramids/multi-scale-feature-pyramids.md) — Extracts object features at different resolutions to detect objects of varying sizes across network layers.
- [Knowledge Distillation](https://awesome-repositories.com/f/artificial-intelligence-ml/knowledge-distillation.md) — Employs a teacher-student framework where a deeper lead model guides a smaller head model to improve performance.
- [Label Assignment Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/label-assignment-strategies.md) — Optimally assigns positive and negative samples during training based on predicted confidence scores.
- [Bottleneck Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/neural-network-layers/convolution-layers/bottleneck-layers.md) — Reduces computational load by compressing and expanding channel dimensions within convolution layers.
- [Edge AI Model Deployment](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/local-and-on-device-inference/edge-ai-model-deployment.md) — Optimizes and deploys trained models for efficient inference on production servers and embedded edge devices.
- [Model Format Converters](https://awesome-repositories.com/f/artificial-intelligence-ml/model-format-converters.md) — Converts trained models into hardware-specific formats for deployment across diverse operating systems. ([source](https://github.com/wongkinyiu/yolov7#readme))
- [Model Weight Converters](https://awesome-repositories.com/f/artificial-intelligence-ml/model-weight-converters.md) — Converts trained weights into formats compatible with external inference servers and production environments. ([source](https://github.com/wongkinyiu/yolov7#readme))
- [Training Optimizations](https://awesome-repositories.com/f/artificial-intelligence-ml/training-optimizations.md) — Implements lightweight architectural improvements that increase accuracy without adding inference cost per image.