SegFormer (b0-sized) 模型在CityScapes上的微调结果

SegFormer 模型在分辨率为1024x1024的CityScapes数据集上进行了微调。该模型最初由Xie等人在论文 SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers 中提出，并在论文 this repository 中首次发布。

免责声明：SegFormer团队未为该模型编写模型卡片，因此本模型卡片由Hugging Face团队编写。

模型描述

SegFormer由分层Transformer编码器和轻量级全MLP解码头组成，对语义分割基准测试（如ADE20K和Cityscapes）的结果非常出色。分层Transformer首先在ImageNet-1k上进行预训练，然后添加解码器头并一起在下游数据集上进行微调。

预期用途及限制

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

如何使用

以下是如何使用此模型将COCO 2017数据集的图像分类为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-1024-1024")
model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-1024-1024")

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，请参阅 documentation 。

许可证

该模型的许可证可以在 here 找到。

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}
}