SegFormer (b5-sized)模型在CityScapes上进行精调

SegFormer模型在分辨率为640x1280的CityScapes数据集上进行了精调。该模型在Xie等人的论文 SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers 中提出并首次发布于 this repository 。

免责声明：SegFormer发布团队并未为该模型撰写模型卡，因此本模型卡是由Hugging Face团队编写的。

模型描述

SegFormer由一个分层Transformer编码器和一个轻量级全MLP解码头组成，可在ADE20K和CityScapes等语义分割基准上取得出色的结果。分层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进行整体微调。

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 ，寻找您感兴趣的任务的精调版本。

使用方法

以下是使用该模型将COCO 2017数据集中的图像分类为1,000个ImageNet类别之一的方法：

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

feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-640-1280")
model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-640-1280")

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)

有关更多代码示例，请参考 documentation 。

许可证

有关该模型的许可证信息，请参见 here 。

BibTeX引用和引用信息

@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}
}