模型:
microsoft/swin-base-patch4-window12-384-in22k
Swin Transformer模型在ImageNet-21k(1400万张图像,21,841个类别)数据集上进行了预训练,图像分辨率为384x384。该模型由Liu等人在论文中提出,并于 this repository 首次发布。
声明:发布Swin Transformer的团队并未为该模型编写模型卡片,因此本模型卡片由Hugging Face团队编写。
Swin Transformer是Vision Transformer的一种类型。它通过在深层中合并图像块(以灰色显示)来构建层次化特征图,并且由于仅在每个局部窗口(以红色显示)内计算自注意力,其计算复杂度与输入图像大小线性相关。因此,它可以作为图像分类和密集识别任务的通用骨干网络。相比之下,之前的视觉Transformer只产生低分辨率的特征图,并且由于在全局范围内计算自注意力,其计算复杂度与输入图像大小呈二次关系。
您可以使用原始模型进行图像分类。请查看 model hub 以寻找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数据集中的图像分类为1000个ImageNet类别之一的示例:
from transformers import AutoFeatureExtractor, SwinForImageClassification 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 = AutoFeatureExtractor.from_pretrained("microsoft/swin-base-patch4-window12-384-in22k") model = SwinForImageClassification.from_pretrained("microsoft/swin-base-patch4-window12-384-in22k") 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,可以参考 documentation 。
@article{DBLP:journals/corr/abs-2103-14030, author = {Ze Liu and Yutong Lin and Yue Cao and Han Hu and Yixuan Wei and Zheng Zhang and Stephen Lin and Baining Guo}, title = {Swin Transformer: Hierarchical Vision Transformer using Shifted Windows}, journal = {CoRR}, volume = {abs/2103.14030}, year = {2021}, url = {https://arxiv.org/abs/2103.14030}, eprinttype = {arXiv}, eprint = {2103.14030}, timestamp = {Thu, 08 Apr 2021 07:53:26 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-14030.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }