Skip to content
ModelListedExternal
Download

LibreRTMDetl

RTMDet-L COCO detector, repackaged for the LibreYOLO framework.

KindOtherVersionRevision 6eaf968Cgrade

Model source

Kind
Other
File size
200–218 MB
Version
vRevision 6eaf968
Updated
Oct 12, 2026
Downloads
0
Source
Hugging Face

Source description

LibreRTMDetl

RTMDet-L COCO detector, repackaged for the LibreYOLO framework.

Source

Derived from https://github.com/open-mmlab/mmdetection at commit cfd5d3a985b0249de009b67d04f37263e11cdf3d and upstream checkpoint: https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet_l_8xb32-300e_coco/rtmdet_l_8xb32-300e_coco_20220719_112030-5a0be7c4.pth.

Copyright (c) 2018-2023 OpenMMLab. Licensed under the Apache License, Version 2.0.

Modifications

EMA weights were selected from the upstream checkpoint. data_preprocessor.* and batch-tracking buffers were omitted, bbox_head. keys were renamed to head., and the loaded state dict was saved with LibreYOLO checkpoint metadata schema v1.0. Learned model parameters are otherwise preserved.

Validation

This file was validated locally with LibreYOLO checkpoint metadata schema v1.0, loaded through LibreYOLO, and evaluated on coco128.yaml with workers=0, batch=8, conf=0.001, iou=0.6.

MetricValue
COCO128 mAP50-950.6332
COCO128 mAP500.8091
SHA256b7edb1046588c516392421464dbd29689433fe442c2ce2d4fc46860b01981960
File size200.2 MB

License

Apache License 2.0. See the LICENSE and NOTICE files in this repository.

Sources

1 source
Hugging FacePrimaryVersion 6eaf968e8bb7f0258485f5f465f935bd266a06cc
huggingface.co/LibreYOLO/LibreRTMDetl/tree/6eaf968e8bb7f0258485f5f465f935bd266a06cc

Verified Aug 26

Model artifacts

2 artifacts

LibreRTMDetl.onnx

onnx · 218 MB · SHA-256 e9cfaa1efc40…b34e · Hugging Face

Download

LibreRTMDetl.pt

pt · 200 MB · SHA-256 b7edb1046588…1960 · Hugging Face

Download

Source excerpts

2 excerpts

--- license: apache-2.0 library_name: libreyolo tags: - object-detection - rtmdet - mmdetection --- # LibreRTMDetl RTMDet-L COCO detector, repackaged for the [LibreYOLO](https://github.com/LibreYOLO/libreyolo) framework. ## Source Derived from [https://github.com/open-mmlab/mmdetection](https://github.com/open-mmlab/mmdetection) at commit `cfd5d3a985b0249de009b67d04f37263e11cdf3d` and upstream checkpoint: `https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet_l_8xb32-300e_coco/rtmdet_l_8xb32-300e_coco_20220719_112030-5a0be7c4.pth`. Copyright (c) 2018-2023 OpenMMLab. Licensed under the Apache License, Version 2.0. ## Modifications EMA weights were selected from the upstream checkpoint. `data_preprocessor.*` and batch-tracking buffers were omitted, `bbox_head.` keys were renamed to `head.`, and the loaded state dict was saved with LibreYOLO checkpoint metadata schema v1.0. Learned model parameters are otherwise preserved. ## Validation This file was validated locally with LibreYOLO checkpoint metadata schema v1.0, loaded through `LibreYOLO`, and evaluated on `coco128.yaml` with `workers=0`, `batch=8`, `conf=0.001`, `iou=0.6`. | Metric | Value | |---|---:| | COCO128 mAP50-95 | 0.6332 | | COCO128 mAP50 | 0.8091 | | SHA256 | `b7edb1046588c516392421464dbd29689433fe442c2ce2d4fc46860b01981960` | | File size | 200.2 MB | ## License Apache License 2.0. See the [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE) files in this repository.

Source context: 0 downloads · 0 likes · Pipeline object-detection · Library libreyolo · Repo LibreYOLO/LibreRTMDetl