Task
Object Detection
R
PekingU/rtdetr_v2_r18vd
Object Detection·PekingU· 97.1K· 6
transformers
apache-2.0
Object Detection
20.2M params
dataset:cocoarxiv:2407.17140license:apache-2.0deploy:azureregion:us
The RT-DETRv2 model was proposed in RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer by Wenyu Lv, Yian Zhao, Qinyao Chang, Kui Huang, Guanzhong Wang, Yi Liu. RT-DETRv2 refines RT-DETR by introducing selective multi-scale feature extraction, a discrete sampling operator for broader deployment compatibility, and improved training strategies like dynamic data augm
# pull & run locally
pip install mlforge-sdk && mlforge pull PekingU/rtdetr_v2_r18vd
pip install mlforge-sdk && mlforge pull PekingU/rtdetr_v2_r18vd
Model details
Provider
PekingU
Framework
transformers
Parameters
20.2M
Size
77 MB
License
apache-2.0
Downloads
97.1K
Likes
6
Paper
arXiv:2407.17140
Updated
2025-02-06
About PekingU/rtdetr_v2_r18vd
The RT-DETRv2 model was proposed in RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer by Wenyu Lv, Yian Zhao, Qinyao Chang, Kui Huang, Guanzhong Wang, Yi Liu. RT-DETRv2 refines RT-DETR by introducing selective multi-scale feature extraction, a discrete sampling operator for broader deployment compatibility, and improved training strategies like dynamic data augmentation and scale-adaptive hyperparameters. These changes enhance flexibility and practicality while maintaining real-time performance.