dmlc/gluon-cvGitHub
choose if your stack is Gluon/MXNet and you need a full CV toolkit with Apache-2.0, though it is stale.
Gluon CV Toolkit
- 5.9k
- Python
- Apache-2.0
dormant1.9y ago
ultralytics/ultralytics Alternatives
computer vision object detection / YOLO
Ultralytics YOLO library for object detection, instance/semantic segmentation, classification, pose estimation, and tracking in PyTorch.
Same job, different approach
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
PaddlePaddle/PaddleDetectionGitHub
choose if you are in the PaddlePaddle ecosystem and need Apache-2.0 with detection, tracking, and pose.
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
- 14.4k
- Python
- Apache-2.0
active5mo ago
IDEA-Research/detrexGitHub
choose if you prefer DETR-style transformer detection over YOLO.
detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.
- 2.3k
- Python
- Apache-2.0
slowing1.1y ago
Older generation, or narrower
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
open-mmlab/mmyoloGitHub
choose if you need OpenMMLab/MMDetection ecosystem integration, but it is stale and older.
OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.
- 3.5k
- Python
- GPL-3.0
dormant2.2y ago
xingyizhou/CenterNetGitHub
choose for center-point detection research code, but it is unmaintained.
Object detection, 3D detection, and pose estimation using center point detection:
- 7.6k
- Python
- MIT
dormant3.6y ago
lucasjinreal/yolov7_d2GitHub
choose if you want Transformer-based YOLOv7 with TensorRT, but it is stale research code.
🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥
- 3.1k
- Python
- GPL-3.0
dormant2.9y ago
CMU-Perceptual-Computing-Lab/openposeGitHub
choose if you need production-grade multi-person 2D keypoints with body/hand/face support, but it only covers pose.
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
- 34.5k
- C++
- NOASSERTION
dormant2.2y ago
MVIG-SJTU/AlphaPoseGitHub
choose for accurate multi-person pose estimation, but it is stale and narrower than the seed.
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
- 8.6k
- Python
- NOASSERTION
dormant2.4y ago
THU-MIG/yolov10GitHub
choose if you specifically want YOLOv10's end-to-end detection, but you lose the multi-task API of Ultralytics.
YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]
- 11.3k
- Python
- AGPL-3.0
dormant1.6y ago
Listed as an alternative to
These projects were analysed and named ultralytics among their alternatives. The relationship is not symmetric — how ultralytics rates them is a separate judgement, made when ultralytics is analysed in its own right.
WongKinYiu/yolov7GitHub
calls ultralytics “Choose for a current, actively maintained all-in-one YOLO framework with YOLOv8/11 and segmentation/pose/classification support.”
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
14.2kJupyter Notebookdormant
PaddlePaddle/PaddleDetectionGitHub
calls ultralytics “State-of-the-art PyTorch toolkit covering detection, segmentation, pose, and tracking — choose for Ultralytics' API, but mind AGPL license.”
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
14.4kPythonactive
THU-MIG/yolov10GitHub
calls ultralytics “Use it for a broader, actively-maintained YOLO ecosystem with multiple models and task support.”
YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]
11.3kPythondormant
roboflow/rf-detrGitHub
calls ultralytics “choose it when you want YOLO-family CNN models with an actively maintained training/export/deployment codebase.”
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
9.1kPythonactive
xingyizhou/CenterNetGitHub
calls ultralytics “Choose when you want a continuously maintained YOLO framework for detection/segmentation/pose with easy pip workflow, but note AGPL-3.0 license vs MIT and a different model family.”
Object detection, 3D detection, and pose estimation using center point detection:
7.6kPythondormant
AILab-CVC/YOLO-WorldGitHub
calls ultralytics “Choose it for the most maintained, export-friendly real-time detector stack when fixed-class training is acceptable.”
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
6.5kPythondormant
fastai/fastaiGitHub
calls ultralytics “Narrower CV-focused library for YOLO detection/segmentation, choose it instead of fastai for object-detection-centric projects.”
The fastai deep learning library
28.1kJupyter Notebookactive