cvat 开源项目推荐（89 个）

Koldim2001 /COCO_to_YOLOv8

将COCO注释（CVAT）转换为YOLO-seg（实例分段）和YOLO-obb（定向边界盒检测）的注释

laclouis5 /globox

读取和转换对象检测数据集（COCO、YOLO、PascalVOC、LabelMe、CVAT、OpenImage等）的包并使用COCO和PascalVOC指标对其进行评估。

BelickNicko /AutoCVAT

Use this project to automatically annotate your dataset for free in CVAT

Koldim2001 /Unet-pytorch-training

Репозиторий для обучения нейросетевых моделей по семантической сегментации + пример использования моделей на практике

asujaykk /Road-segmentation-UNET-model

This project aims to develope a Road-Segmentation model for Advanced Driver Assistance System (ADAS)

aws-samples /cvat-on-aws-china

该项目在 GitHub 上没有填写描述

Imageomics /kabr-tools

Modular tools pipeline for annotating animal behavior. These were specifically designed during construction of the KABR dataset, and have been generalized with the KABR process provided as a reference example.

bessszilard /Garbage-detection

该项目在 GitHub 上没有填写描述

MacroMan5 /autotrain-yolo

YOLO training toolkit with Claude Code skills — dataset management, experiment tracking, HP tuning via model.tune(), active learning with CVAT, ONNX export. Supports YOLO11 & YOLO26.

THINK989 /Automatic_License_Plate_Detector_for_Adverse_Environments

该项目在 GitHub 上没有填写描述

antwxne /CVAT_python_wrapper

Python wrapper for cvat

Koldim2001 /Auto_annotation_CVAT

Создание автоматической аннотации с использованием предобученной модели YOLOv5

hardikdava /cvat_plugins

This reposity contains some serverless functionality for auto annotations

holtvogt /tracklet_parser

A parser for tracklet labels in KITTI Raw Format 1.0 created by the Computer Vision Annotation Tool (CVAT).

Yashmenaria1 /Car-Brand-Detection

The "Car Brand Detection" project aims to develop an efficient system for identifying car brands from images using computer vision techniques. Utilizing a labeled dataset created with CVAT and training with the YOLO v8 model, the project seeks to achieve high accuracy in recognizing various car brands in real-world scenarios.

rseng /google-cloud-cvat

Documentation for deployment of cvat on Google Cloud (under development)

xaerincl /Yolo_Autolabel

Yolo autolabel. It can export the dataset to CVAT format for editing or exporting to another format

ubiobio /TallerYolov8

Código para entrenamiento de modelo para detección de objetos con algoritmo Yolov8 de Ultralytics

omigutin /annotation_parser

AnnotationParser is a universal Python library that parses annotation files from different formats (LabelMe, COCO, VOC, etc.) into a single unified Shape data structure. This allows you to work with annotations using a consistent interface, regardless of the original format.

greenroom-robotics /nuclio_lighting_flash

Connects Nuclio / CVAT to Lighting flash ML models