模型:
nvidia/segformer-b5-finetuned-ade-640-640
SegFormer模型在分辨率为640x640的ADE20k数据集上进行了微调。这是由Xie等人在 SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers 论文中介绍并首次发布的。
声明:发布SegFormer模型的团队没有为此模型编写模型卡片,所以这个模型卡片是由Hugging Face团队编写的。
SegFormer由一个分层Transformer编码器和一个轻量级全MLP解码头组成,在ADE20K和Cityscapes等语义分割基准测试上取得了很好的结果。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联合微调。
您可以使用原始模型进行语义分割。查看 model hub 以寻找您感兴趣的任务的微调版本。
这是如何使用此模型将COCO 2017数据集中的图像分类为1,000个ImageNet类别之一的方法:
from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation from PIL import Image import requests feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b5-finetuned-ade-512-512") model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b5-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)
有关更多代码示例,请参阅 documentation 。
可以在 here 找到此模型的许可证。
@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} }