Skip to content
ModelListedExternal
Download

LibreDEIMn

DEIM-N (HGNetv2 backbone) repackaged for the LibreYOLO framework.

KindOtherVersionRevision e9e38bbCgrade

Model source

Kind
Other
File size
14.8–15.0 MB
Version
vRevision e9e38bb
Updated
Oct 13, 2026
Downloads
0
Source
Hugging Face

Source description

LibreDEIMn

DEIM-N (HGNetv2 backbone) repackaged for the LibreYOLO framework.

Source

Detector: Intellindust-AI-Lab/DEIM. Licensed under the Apache License, Version 2.0. Weights derived from upstream deim_hgnetv2_n_coco.pth (DEIM-D-FINE-N, 4M params, 43.0 AP).

DEIM reuses the D-FINE architecture (Peterande/D-FINE) and replaces the classification objective with a Matchability-Aware Loss.

Backbone: HGNetv2 (PP-HGNetV2) from PaddlePaddle/PaddleClas. Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved. Licensed under the Apache License, Version 2.0.

Modifications

Metadata wrap and file rename only. Learned parameters are unchanged. Conversion script: weights/convert_deim_weights.py.

License

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

Sources

1 source
Hugging FacePrimaryVersion e9e38bbcef17519dcd86d2e92a7b824db35ca83c
huggingface.co/LibreYOLO/LibreDEIMn/tree/e9e38bbcef17519dcd86d2e92a7b824db35ca83c

Verified Aug 26

Model artifacts

2 artifacts

LibreDEIMn.onnx

onnx · 15.0 MB · SHA-256 cf94979f4dcd…3bd5 · Hugging Face

Download

LibreDEIMn.pt

pt · 14.8 MB · SHA-256 21e97f123126…3d11 · Hugging Face

Download

Source excerpts

2 excerpts

--- license: apache-2.0 library_name: libreyolo tags: - object-detection - deim - d-fine - detr --- # LibreDEIMn DEIM-N (HGNetv2 backbone) repackaged for the [LibreYOLO](https://github.com/LibreYOLO/libreyolo) framework. ## Source Detector: [Intellindust-AI-Lab/DEIM](https://github.com/Intellindust-AI-Lab/DEIM). Licensed under the Apache License, Version 2.0. Weights derived from upstream `deim_hgnetv2_n_coco.pth` (DEIM-D-FINE-N, 4M params, 43.0 AP). DEIM reuses the D-FINE architecture ([Peterande/D-FINE](https://github.com/Peterande/D-FINE)) and replaces the classification objective with a Matchability-Aware Loss. Backbone: HGNetv2 (PP-HGNetV2) from [PaddlePaddle/PaddleClas](https://github.com/PaddlePaddle/PaddleClas). Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved. Licensed under the Apache License, Version 2.0. ## Modifications Metadata wrap and file rename only. Learned parameters are unchanged. Conversion script: [`weights/convert_deim_weights.py`](https://github.com/LibreYOLO/libreyolo/blob/main/weights/convert_deim_weights.py). ## 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/LibreDEIMn