CondadosAI/rtmdet_l_coco

RTMDet-l — acaua mirror (pure-PyTorch port)

Pure-PyTorch port of RTMDet-l (52.3M params, COCO box AP 51.5) hosted under CondadosAI/ for use with the acaua computer vision library.

The architecture has been re-implemented in pure PyTorch under acaua.adapters.rtmdet — no mmcv, no mmengine, no mmdet, no trust_remote_code. The weights in this mirror are converted from the upstream mmdet .pth checkpoint to safetensors with the acaua adapter's state_dict key naming. They are NOT drop-in compatible with mmdet — they're designed to load cleanly into our nn.Module tree.

Provenance

Upstream code	open-mmlab/mmdetection @ cfd5d3a985 (Apache-2.0)
Upstream weights URL	https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet_l_8xb32-300e_coco/rtmdet_l_8xb32-300e_coco_20220719_112030-5a0be7c4.pth
Upstream weights SHA256	5a0be7c4a8123d1e634ce09b08682af373f503de2040e1532d254791f9332cec
Conversion script	scripts/convert_rtmdet.py
Paper	Lyu et al., "RTMDet: An Empirical Study of Designing Real-Time Object Detectors", arXiv:2212.07784
Mirrored on	2026-04-20
Mirrored by	CondadosAI/acaua

Usage

import acaua

model = acaua.Model.from_pretrained("CondadosAI/rtmdet_l_coco")
results = model.predict("image.jpg")
print(results.boxes, results.scores, results.labels)

License and attribution

Redistributed under Apache-2.0, consistent with the upstream code (open-mmlab/mmdetection) and the weights released on download.openmmlab.com. The acaua adapter is itself a derivative work of the upstream PyTorch implementation — see NOTICE for the required attribution chain (code AND weights).

Citation

@misc{lyu2022rtmdet,
      title={RTMDet: An Empirical Study of Designing Real-Time Object Detectors},
      author={Chengqi Lyu and Wenwei Zhang and Haian Huang and Yue Zhou and Yudong Wang and Yanyi Liu and Shilong Zhang and Kai Chen},
      year={2022},
      eprint={2212.07784},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}