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.
About ultralytics
ultralytics/ultralytics
Ultralytics YOLO 🚀
Supports multi-task computer vision workflows including object tracking, instance segmentation, image classification, and pose estimation through a unified PyTorch-based architecture. Offers both CLI and Python API interfaces with pre-trained model weights, enabling rapid deployment across detection, segmentation, and estimation pipelines without extensive configuration.
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/
Implements decoupled head architecture separating classification and localization branches, with dynamic label assignment during training to improve convergence. Provides multiple model scales from Nano (0.91M parameters) to X (99.1M parameters) optimized for various deployment scenarios, plus native PyTorch training with mixed-precision and distributed multi-machine support.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work