PaddleDetection
mmtracking
| PaddleDetection | mmtracking | |
|---|---|---|
| 7 | 7 | |
| 12,074 | 3,382 | |
| 0.9% | 1.6% | |
| 6.5 | 1.5 | |
| 6 days ago | 8 months ago | |
| Python | Python | |
| Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
PaddleDetection
-
[R]DETRs Beat YOLOs on Real-time Object Detection
Our RTDETR-L achieves 53.0% AP on COCO val2017 and 114 FPS on T4 GPU, while RT-DETR-X achieves 54.8% AP and 74 FPS, outperforming all YOLO detectors of the same scale in both speed and accuracy. Furthermore, our RTDETR-R50 achieves 53.1% AP and 108 FPS, outperforming DINO-Deformable-DETR->R50 by 2.2% AP in accuracy and by about 21 times in FPS. Source code and pretrained models will be available at PaddleDetection1 (https://github.com/PaddlePaddle/PaddleDetection) .
-
YOLO series models ALL IN ONE
In order to make it easier for everyone to use the YOLO series model, we have open-sourced this collections. You can experience PP-YOLOE+, YOLOv8, RTMDet, DAMO-YOLO, YOLOv7, YOLOv6, YOLOX, YOLOv5...just in https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/feature_models/PaddleYOLO_MODEL_en.md
- YOLO series Models ALL IN ONE
- Paddledetection - Object detection toolkit based on paddlepaddle
-
Baidu Researchers Propose PP-YOLOE Object Detector: an Evolved Version of YOLO Achieving SOTA Performance in Object Detection
Code for https://arxiv.org/abs/2203.16250 found: https://github.com/PaddlePaddle/PaddleDetection
Github: https://github.com/PaddlePaddle/PaddleDetection
- Imagine what historians will say about naming convention for pre trained models in 50 years…
mmtracking
-
Tracking sets of Keypoints by Person
I suggest to try the top down approach with the https://openmmlab.com/ open source package. The openmmlab provides multiple algorithms, datasets and pretrained models for various computer vision tasks. Start with mmpose video demo that integrates detection and pose estimation. You can add later tracking with https://github.com/open-mmlab/mmtracking to track the poses in time.
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
MMTracking: OpenMMLab video perception toolbox and benchmark.
- [P]We have supported Quasi-Dense Similarity Learning for Multiple Object Tracking.
- [p]We have supported Quasi-Dense Similarity Learning for Multiple Object Tracking
- MMTracking have supported Quasi-Dense Similarity Learning for Multiple Object Tracking.
- MMTracking Supports Quasi-Dense Similarity Learning for Multiple Object Tracking
-
Help combining custom detector (yolo) with a tracker.
Implementations exist, like https://github.com/open-mmlab/mmtracking
What are some alternatives?
mmdetection - OpenMMLab Detection Toolbox and Benchmark
ByteTrack - [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
faster-rcnn.pytorch - A faster pytorch implementation of faster r-cnn
FastMOT - High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀
medicaldetectiontoolkit - The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
norfair - Lightweight Python library for adding real-time multi-object tracking to any detector.
SOLO - SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
Yolov7_StrongSORT_OSNet - Real-time multi-camera multi-object tracker using YOLOv7 and StrongSORT with OSNet
BCNet - Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]
mmyolo - OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.
DeepSORT - support deepsort and bytetrack MOT(Multi-object tracking) using yolov5 with C++
UniTrack - [NeurIPS'21] Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking and Segmentation (MOTS), Pose Tracking, Video Instance Segmentation (VIS), and class-agnostic MOT (e.g. TAO dataset).