object detection
Ultralytics YOLOv3 is a PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and export.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose when you want a broader object-detection toolbox under Apache-2.0 and the PaddlePaddle framework.
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Choose when you want the YOLOv6 architecture and can switch to this PyTorch/GPL-3.0 codebase.
YOLOv6: a single-stage object detection framework dedicated to industrial applications.
Choose when you need open-vocabulary object detection within a YOLO-like framework.
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
Choose when you want the YOLOv7 architecture and can migrate from the YOLOv3 codebase.
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Choose if you prefer a keypoint-based detector with MIT license and a pure-PyTorch codebase.
Object detection, 3D detection, and pose estimation using center point detection:
These projects were analysed and named yolov3 among their alternatives. The relationship is not symmetric — how yolov3 rates them is a separate judgement, made when yolov3 is analysed in its own right.
calls yolov3 “Choose it if you require a lightweight, well-documented YOLO version for legacy or edge deployments.”
YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]
calls yolov3 “Only for legacy YOLOv3 pipelines and tiny-model exports; much lower accuracy and no text prompts.”
[CVPR 2024] Real-Time Open-Vocabulary Object Detection