Mit B5 Finetuned Sidewalk Semantic

🚀 基于人行道语义数据集微调的SegFormer（b5尺寸）模型

本项目是在SegmentsAI的sidewalk-semantic数据集上微调的SegFormer模型。该模型由Xie等人在论文SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers中提出，并首次在此仓库中发布，可用于高效的图像语义分割任务。

🚀 快速开始

本模型是基于SegmentsAI的sidewalk-semantic数据集对SegFormer进行微调得到的。它由Xie等人在论文SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers中提出，并首次在此仓库中发布。

✨ 主要特性

SegFormer由一个分层的Transformer编码器和一个轻量级的全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的成绩。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。

💻 使用示例

基础用法

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

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)

feature_extractor = SegformerFeatureExtractor.from_pretrained("zoheb/mit-b5-finetuned-sidewalk-semantic")
model = SegformerForImageClassification.from_pretrained("zoheb/mit-b5-finetuned-sidewalk-semantic")

inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits

# model predicts one of the 35 Sidewalk classes
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])

你可以在这里查看详细的笔记本示例。更多代码示例请参考文档。

📄 许可证

该模型的许可证可在这里找到。

📚 详细文档

BibTeX引用

@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}
}