ultralytics and YOLOX

YOLOX is an alternative YOLO implementation that competes with Ultralytics' YOLOv3-v5 lineage by offering anchor-free detection with different backend support, making them direct competitors in the object detection framework space.

ultralytics
87
Verified
YOLOX
62
Established
Maintenance 22/25
Adoption 15/25
Maturity 25/25
Community 25/25
Maintenance 2/25
Adoption 10/25
Maturity 25/25
Community 25/25
Stars: 54,333
Forks: 10,447
Downloads:
Commits (30d): 151
Language: Python
License: AGPL-3.0
Stars: 10,373
Forks: 2,448
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
No risk flags
Stale 6m No Dependents

About ultralytics

ultralytics/ultralytics

Ultralytics YOLO 🚀

This project helps anyone needing to automatically identify, classify, or track objects and actions within images or videos. You provide visual media, and it outputs labeled bounding boxes, segmentation masks, or keypoints for recognized items. This is ideal for roles like security analysts, manufacturing quality control, agricultural inspectors, or retail inventory managers.

object-detection video-surveillance quality-inspection asset-tracking image-analysis

About YOLOX

Megvii-BaseDetection/YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

YOLOX helps developers quickly implement high-performance object detection in computer vision applications. It takes images or video frames as input and outputs bounding boxes and classifications for objects within them. This tool is ideal for machine learning engineers and researchers who need to integrate efficient and accurate object detection capabilities into their systems.

object-detection computer-vision machine-learning-engineering real-time-processing AI-development

Scores updated daily from GitHub, PyPI, and npm data. How scores work