模型:
nvidia/segformer-b2-finetuned-ade-512-512
SegFormer模型在分辨率为512x512的ADE20k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 this repository 中首次发布。
免责声明:发布SegFormer模型的团队没有为这个模型编写模型卡片,所以这个模型卡片是由Hugging Face团队编写的。
SegFormer包括一个层次化的Transformer编码器和一个轻量级的全MLP解码头,可以在ADE20K和Cityscapes等语义分割基准上取得出色的结果。层次化Transformer首先在ImageNet-1k上进行预训练,之后添加解码头,并在下游数据集上进行整体微调。
您可以使用原始模型进行语义分割。请参考 model hub 查找您感兴趣的任务的微调版本。
下面是如何使用该模型将COCO 2017数据集中的图像分类为1,000个ImageNet类别之一的示例:
from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation from PIL import Image import requests feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b2-finetuned-ade-512-512") model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b2-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)
关于更多代码示例,我们参考 documentation 。
@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} }