模型:
nvidia/mit-b5
SegFormer编码器在Imagenet-1k上进行了微调。它由Xie等人在论文中介绍,并首次在发布了。
声明:发布SegFormer的团队没有为该模型编写模型卡片,因此此模型卡片是由Hugging Face团队编写的。
SegFormer由分层Transformer编码器和轻量级的全MLP解码头组成,可以在ADE20K和Cityscapes等语义分割基准上取得出色的结果。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整体微调。
此存储库仅包含预训练的分层Transformer,因此可以用于微调目的。
您可以使用此模型进行语义分割的微调。请查看 model hub 以获取您感兴趣的任务的微调版本。
以下是如何使用此模型将COCO 2017数据集的图像分类为1,000个Imagenet类别之一:
from transformers import SegformerFeatureExtractor, SegformerForImageClassification from PIL import Image import requests url = "http://images.cocodataset.org/val2017/000000039769.jpg" image = Image.open(requests.get(url, stream=True).raw) feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/mit-b5") model = SegformerForImageClassification.from_pretrained("nvidia/mit-b5") inputs = feature_extractor(images=image, return_tensors="pt") outputs = model(**inputs) logits = outputs.logits # model predicts one of the 1000 ImageNet classes predicted_class_idx = logits.argmax(-1).item() print("Predicted class:", model.config.id2label[predicted_class_idx])
有关更多代码示例,请参阅 documentation 。
此模型的许可证可以在 here 找到。
@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} }