SegFormer（b0尺寸）模型在ADE20k上经过微调

SegFormer模型在分辨率为512x512的ADE20k数据集上进行了微调。该模型由Xie等人在论文 SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers 中介绍，并于 this repository 首次发布。

免责声明：发布SegFormer的团队未针对此模型撰写模型卡片，因此该模型卡片由Hugging Face团队撰写。

模型描述

SegFormer由分层Transformer编码器和轻量级全MLP解码头组成，在ADE20K和Cityscapes等语义分割基准测试中取得了很好的效果。分层Transformer首先在ImageNet-1k上进行预训练，然后添加解码头并联合在下游数据集上进行微调。

拟合用途和限制

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

使用此模型对COCO 2017数据集的图像进行分类为其中一个1,000个ImageNet类的示例代码如下：

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

processor = SegformerImageProcessor.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-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

此模型的许可证可以在 here 中找到。

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}
}