标签:

• 视觉
• 图像分割 数据集:
• segments/sidewalk-semantic 小部件:
• 图片: https://segmentsai-prod.s3.eu-west-2.amazonaws.com/assets/admin-tobias/439f6843-80c5-47ce-9b17-0b2a1d54dbeb.jpg 示例标题: 布鲁日

基于Segments.ai sidewalk-semantic微调的SegFormer (b0尺寸)模型

该SegFormer模型在Segments.ai的sidewalk-semantic数据集上进行了微调。该模型由Xie等人在论文SegFormer: 基于Transformer的语义分割简单高效设计中提出，并首次发布于此代码库。

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优异成果。分层Transformer首先在ImageNet-1k上进行预训练，随后添加解码头并在下游数据集上共同微调。

使用方法

以下是使用该模型对人行道数据集图像进行分类的方法：

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

feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
model = SegformerForSemanticSegmentation.from_pretrained("segments-tobias/segformer-b0-finetuned-segments-sidewalk")

url = "https://segmentsai-prod.s3.eu-west-2.amazonaws.com/assets/admin-tobias/439f6843-80c5-47ce-9b17-0b2a1d54dbeb.jpg"
image = Image.open(requests.get(url, stream=True).raw)

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

更多代码示例请参阅文档。

BibTeX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}
}