Mit B5 Finetuned Sidewalk Semantic

🚀 基於人行道語義數據集微調的SegFormer（b5尺寸）模型

本項目是在SegmentsAI的sidewalk-semantic數據集上微調的SegFormer模型。該模型由Xie等人在論文SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers中提出，並首次在此倉庫中發佈，可用於高效的圖像語義分割任務。

🚀 快速開始

本模型是基於SegmentsAI的sidewalk-semantic數據集對SegFormer進行微調得到的。它由Xie等人在論文SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers中提出，並首次在此倉庫中發佈。

✨ 主要特性

SegFormer由一個分層的Transformer編碼器和一個輕量級的全MLP解碼頭組成，在ADE20K和Cityscapes等語義分割基準測試中取得了優異的成績。分層Transformer首先在ImageNet - 1k上進行預訓練，然後添加解碼頭，並在下游數據集上進行整體微調。

💻 使用示例

基礎用法

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])

你可以在這裡查看詳細的筆記本示例。更多代碼示例請參考文檔。

📄 許可證

該模型的許可證可在這裡找到。

📚 詳細文檔

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}
}