模型:

nvidia/segformer-b3-finetuned-ade-512-512

英文

SegFormer (b3-sized)模型在ADE20k上微调

SegFormer模型在512x512分辨率下在ADE20k上进行了微调。该模型首次出现在Xie等人的论文 SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers 中,并在 this repository 首次发布。

免责声明:发布SegFormer的团队没有为该模型撰写模型卡片,因此本模型卡片由Hugging Face团队编写。

模型描述

SegFormer由一个层级Transformer编码器和一个轻量级的全连接多层感知器解码头组成,在ADE20K和Cityscapes等语义分割基准上取得了很好的结果。层级Transformer首先在ImageNet-1k上进行预训练,然后添加解码头并在下游数据集上一起进行微调。

预期用途和限制

您可以使用原始模型进行语义分割。请查看 model hub 上您感兴趣的任务的微调版本。

如何使用

以下是如何使用该模型将COCO 2017数据集中的图像分类到1,000个ImageNet类别中的示例:

from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
from PIL import Image
import requests

feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b3-finetuned-ade-512-512")
model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b3-finetuned-ade-512-512")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits  # shape (batch_size, num_labels, height/4, width/4)

更多代码示例,请参阅 documentation

许可证

该模型的许可证可在 here 处找到。

BibTeX条目和引用信息

@article{DBLP:journals/corr/abs-2105-15203,
  author    = {Enze Xie and
               Wenhai Wang and
               Zhiding Yu and
               Anima Anandkumar and
               Jose M. Alvarez and
               Ping Luo},
  title     = {SegFormer: Simple and Efficient Design for Semantic Segmentation with
               Transformers},
  journal   = {CoRR},
  volume    = {abs/2105.15203},
  year      = {2021},
  url       = {https://arxiv.org/abs/2105.15203},
  eprinttype = {arXiv},
  eprint    = {2105.15203},
  timestamp = {Wed, 02 Jun 2021 11:46:42 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2105-15203.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}