Instructions to use LibreYOLO/LibreDFINEx-seg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LibreYOLO
How to use LibreYOLO/LibreDFINEx-seg with LibreYOLO:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
LibreDFINEx-seg
D-FINE-seg X-Large COCO instance segmentation weights repackaged for LibreYOLO.
Source
Derived from ArgoHA/D-FINE-seg (v0.1.0),
upstream checkpoint dfine_seg_x_coco.pt downloaded from
ArgoSA/D-FINE-seg.
Copyright (c) 2026 The D-FINE-seg Authors. Licensed under the
Apache License, Version 2.0.
D-FINE-seg extends D-FINE (Copyright (c) 2024 The D-FINE Authors, Apache-2.0) with a lightweight instance-segmentation mask head.
Modifications
Wrapped the upstream state dict in LibreYOLO checkpoint metadata:
model_family="dfine", size="x", task="segment", nc=80,
and imgsz=640. Learned parameters are unchanged.
See weights/convert_dfine_weights.py in the
LibreYOLO source repository.
Usage
pip install libreyolo
from libreyolo import LibreYOLO
model = LibreYOLO("LibreDFINEx-seg.pt")
results = model("image.jpg", save=True)
License
Apache License 2.0. See the LICENSE and NOTICE
files in this repository.
- Downloads last month
- 122