AS-One

Visit Tool

AS-One is an open-source computer vision library that offers easy and modular detectors, trackers, and SAM. It allows users to run various YOLO models (v9, v8, v7, v6, v5, R, X) with minimal code.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is AS-One?

AS-One is a comprehensive, open-source Python wrapper designed for computer vision tasks, providing an easy and modular interface for object detection, segmentation, tracking, and pose estimation. It supports a wide range of YOLO models, including YOLOv9, v8, v7, v6, v5, R, and X, enabling users to implement these advanced models in under 10 lines of code. The library integrates various tracking algorithms like ByteTrack, DeepSORT, and NorFair, and supports models in ONNX, PyTorch, and CoreML formats. AS-One also includes capabilities for text detection and recognition using models like CRAFT and EasyOCR, and pose estimation with YOLOv8 and YOLOv7-w6. It is ideal for developers and researchers looking for a unified and efficient solution for their computer vision projects.

Best used for

Ideal for developers and data scientists who need to quickly implement and test various computer vision models for object detection, tracking, segmentation, and pose estimation. Especially valuable for integrating multiple YOLO versions and tracking algorithms into projects with minimal code, facilitating rapid prototyping and deployment.

Common actions

detect objects

track objects

segment images

estimate pose

recognize text

"AI Agents"github copilotface swappingworkflowsautomated workflowopen-sourcedeepfakecollaborationlow-code/no-code

Capabilities

Key features

Modular YOLO integration
Multi-algorithm object tracking
Image segmentation (SAM)
Text detection and recognition
Pose estimation
ONNX, PyTorch, CoreML support
Custom trained weights

Target Audience

developerdata scientist

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What YOLO versions does AS-One support?

AS-One supports a wide range of YOLO models, including YOLOv9, v8, v7, v6, v5, R, and X. It also plans to offer support for future YOLO versions as they are released, ensuring up-to-date capabilities.

Can I use custom trained weights with AS-One?

Yes, AS-One allows you to use your custom trained weights for detector models. You can simply provide the path to your weights file when initializing the ASOne class, enabling tailored object detection.

What tracking algorithms are integrated into AS-One?

AS-One integrates several popular tracking algorithms, including ByteTrack, DeepSORT, and NorFair. These can be combined with different YOLO versions to provide robust object tracking capabilities for various applications.

Trending

Subcategories trending in Data & Analytics

Business Intelligence Predictive Analytics Real-Time Analytics Market Research Data Cleaning & Prep Data Pipelines & Integration

Trending

Also listed in

This tool also appears in

AI Agents & Automation › AI Frameworks & Infra Coding & Development › Open Source & Models

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce