UniAD
PaddleDetection
| UniAD | PaddleDetection | |
|---|---|---|
| 1 | 7 | |
| 2,879 | 12,138 | |
| 5.8% | 1.5% | |
| 7.1 | 6.5 | |
| about 2 months ago | 3 days 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.
UniAD
-
Goal-oriented Autonomous Driving (Open Source!)
Code: https://github.com/OpenDriveLab/UniAD (to be released soon)
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…
What are some alternatives?
M2I - M2I is a simple but effective joint motion prediction framework through marginal and conditional predictions by exploiting the factorized relations between interacting agents.
mmdetection - OpenMMLab Detection Toolbox and Benchmark
ByteTrack - [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
mmtracking - OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
faster-rcnn.pytorch - A faster pytorch implementation of faster r-cnn
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.
SOLO - SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
BCNet - Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]
DeepSORT - support deepsort and bytetrack MOT(Multi-object tracking) using yolov5 with C++
multi-object-tracker - Multi-object trackers in Python
RefineMask - RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features (CVPR 2021)
Street-View-House-Numbers-Detection - This project uses yolov5 pre-trained model to solve Street View House Numbers images object detection task.