ModelAufgelistetExtern

LibreSegformerb0 Sem

nvidia-source-code-license-segformer

Quellehuggingface.co/LibreYOLO/LibreSegformerb0-sem/tree/168b312ed32d8fee8f15fe66ab6fe124817b2cbe

ArtOtherVersionLibre Segformerb0 semCBewertung

Modellquelle

Art: Other
Dateigröße: 14,4 MB
Version: vLibre Segformerb0 sem
Aktualisiert: 10. Okt. 2026
Quelle: Hugging Face

Quellenbeschreibung

LibreSegformerb0-sem

SegFormer MiT-b0 (3.8M params) with the all-MLP decode head, fine-tuned on ADE20K (150 classes) at 512x512, repackaged for LibreYOLO.

⚠️ NON-COMMERCIAL WEIGHTS

These weights are not covered by LibreYOLO's permissive license. They derive from NVIDIA's SegFormer release, licensed under the NVIDIA Source Code License, which restricts use to non-commercial research or evaluation purposes only (Section 3.3). That restriction is carried into every derivative work (Section 3.2) and it binds you, the downloader, not just LibreYOLO.

The LibreYOLO code and the SegFormer architecture are unrestricted, as is any model you train from scratch with them. Only these pretrained weights are limited. For commercial use, train from scratch: LibreSegformer(size="b0", nb_classes=N).train(data="your.yaml").

Usage

from libreyolo import LibreSegformer

model = LibreSegformer("LibreSegformerb0-sem.pt")
results = model.predict("image.jpg")
mask = results[0].semantic_mask      # dense 150-class ADE20K mask

Source

Architecture from "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers" (Xie et al., NeurIPS 2021). LibreYOLO's implementation is an independent port of the Apache-2.0 reference in HuggingFace Transformers, with no runtime dependency on it.

Modifications

State-dict key remapping only (upstream segformer. encoder prefix becomes encoder.), plus LibreYOLO checkpoint metadata. Learned parameters are unchanged: the converted checkpoint reproduces upstream logits bit-exactly (max abs difference 0.0 in float64). See weights/convert_segformer_weights.py.

Accuracy

ADE20K val (2000 images), single scale:

	mIoU
LibreYOLO `model.val(data="ade20k.yaml")`	36.5
Upstream authors, reported	37.4

LibreYOLO's validator letterboxes to a fixed square canvas; the authors evaluate with a ratio-preserving resize, which is worth roughly a point. The converted weights reproduce the upstream model's logits bit-exactly (max abs difference 0.0 in float64), so any remaining difference is evaluation protocol, not conversion.

License

NVIDIA Source Code License for SegFormer (non-commercial). See LICENSE and NOTICE.

Quellen

1 Quelle

Hugging FacePrimärVersion 168b312ed32d8fee8f15fe66ab6fe124817b2cbe

huggingface.co/LibreYOLO/LibreSegformerb0-sem/tree/168b312ed32d8fee8f15fe66ab6fe124817b2cbe

Verifiziert 10. Okt.

Modellartefakte

1 Artefakt

LibreSegformerb0-sem.pt

pt · 14,4 MB · SHA-256 37a5915c12d5…1bbf · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge

Readme1. Aug.huggingface.co/LibreYOLO/LibreSegformerb0-sem

--- license: other license_name: nvidia-source-code-license-segformer license_link: https://github.com/NVlabs/SegFormer/blob/master/LICENSE library_name: libreyolo pipeline_tag: image-segmentation datasets: - scene_parse_150 tags: - semantic-segmentation - segformer - ade20k - non-commercial --- # LibreSegformerb0-sem SegFormer MiT-b0 (3.8M params) with the all-MLP decode head, fine-tuned on ADE20K (150 classes) at 512x512, repackaged for [LibreYOLO](https://github.com/LibreYOLO/libreyolo). > ## ⚠️ NON-COMMERCIAL WEIGHTS > > These weights are **not** covered by LibreYOLO's permissive license. They > derive from NVIDIA's SegFormer release, licensed under the > [NVIDIA Source Code License](https://github.com/NVlabs/SegFormer/blob/master/LICENSE), > which restricts **use** to **non-commercial research or evaluation purposes > only** (Section 3.3). That restriction is carried into every derivative work > (Section 3.2) and it binds you, the downloader, not just LibreYOLO. > > The LibreYOLO **code** and the SegFormer **architecture** are unrestricted, as > is any model you train from scratch with them. Only these pretrained weights > are limited. For commercial use, train from scratch: > `LibreSegformer(size="b0", nb_classes=N).train(data="your.yaml")`. ## Usage ```python from libreyolo import LibreSegformer model = LibreSegformer("LibreSegformerb0-sem.pt") results = model.predict("image.jpg") mask = results[0].semantic_mask # dense 150-class ADE20K mask ``` ## Source Converted from [nvidia/segformer-b0-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512). Copyright (c) 2021, NVIDIA Corporation & affiliates. Licensed under the NVIDIA Source Code License for SegFormer. Architecture from "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers" (Xie et al., NeurIPS 2021). LibreYOLO's implementation is an independent port of the Apache-2.0 reference in HuggingFace Transformers, with no runtime dependency on it. ## Modifications State-dict key remapping only (upstream `segformer.` encoder prefix becomes `encoder.`), plus LibreYOLO checkpoint metadata. Learned parameters are unchanged: the converted checkpoint reproduces upstream logits **bit-exactly** (max abs difference 0.0 in float64). See [`weights/convert_segformer_weights.py`](https://github.c...

Note1. Aug.huggingface.co/LibreYOLO/LibreSegformerb0-sem

Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Library libreyolo · Repo LibreYOLO/LibreSegformerb0-sem