rtdetr_r50vd

RT-DETR R50-vd (COCO + Objects365) — acaua mirror

Apache-2.0 mirror hosted under CondadosAI/ for use with the acaua computer vision library.

This is a 1:1 byte-identical copy of the upstream PekingU weights at the pinned commit shown below. We do not modify weights or configuration. The purpose of the mirror is license hygiene: acaua's core promise is that every shipped weight has an auditable, declared Apache-2.0 upstream. Mirroring lets us pin a specific revision so the audit claim stays verifiable even if upstream rewrites history.

Provenance

Usage via acaua

import acaua
model = acaua.Model.from_pretrained("CondadosAI/rtdetr_r50vd")
results = model.predict("image.jpg")
for r in results:
    print(r.boxes, r.labels, r.scores)

Usage via 🤗 Transformers

This mirror is drop-in compatible with the upstream PekingU repo:

from transformers import AutoModelForObjectDetection, AutoImageProcessor
model = AutoModelForObjectDetection.from_pretrained("CondadosAI/rtdetr_r50vd")
processor = AutoImageProcessor.from_pretrained("CondadosAI/rtdetr_r50vd")

License and attribution

Redistributed under Apache License 2.0, consistent with the upstream declaration at every tier (RT-DETR → PaddleClas → PekingU conversion).

See NOTICE for required attribution to upstream contributors (Baidu, RT-DETR authors, PaddleClas maintainers, PekingU / HF conversion contributors).

Citation

@article{zhao2023detrs,
  title={DETRs Beat YOLOs on Real-time Object Detection},
  author={Zhao, Yian and Lv, Wenyu and Xu, Shangliang and Wei, Jinman and Wang, Guanzhong and Dang, Qingqing and Liu, Yi and Chen, Jie},
  journal={arXiv preprint arXiv:2304.08069},
  year={2023}
}