模型:
facebook/convnext-large-224-22k-1k
ConvNeXT模型在ImageNet-22k上进行了预训练,并在224x224分辨率的ImageNet-1k上进行了微调。它在Liu等人的论文 A ConvNet for the 2020s 中首次发布。
声明:发布ConvNeXT团队没有为该模型编写模型卡片,因此这个模型卡片是由Hugging Face团队编写的。
ConvNeXT是一个纯卷积模型(ConvNet),受到Vision Transformers设计的启发,声称超越它们。作者从ResNet开始,通过借鉴Swin Transformer的设计进行“现代化”。
您可以使用原始模型进行图像分类。查看 model hub 以查找您感兴趣的任务上的微调版本。
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类别之一的示例:
from transformers import ConvNextFeatureExtractor, ConvNextForImageClassification import torch from datasets import load_dataset dataset = load_dataset("huggingface/cats-image") image = dataset["test"]["image"][0] feature_extractor = ConvNextFeatureExtractor.from_pretrained("facebook/convnext-large-224-22k-1k") model = ConvNextForImageClassification.from_pretrained("facebook/convnext-large-224-22k-1k") inputs = feature_extractor(image, return_tensors="pt") with torch.no_grad(): logits = model(**inputs).logits # model predicts one of the 1k ImageNet classes predicted_label = logits.argmax(-1).item() print(model.config.id2label[predicted_label]),
更多代码示例,请参阅 documentation 。
@article{DBLP:journals/corr/abs-2201-03545, author = {Zhuang Liu and Hanzi Mao and Chao{-}Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie}, title = {A ConvNet for the 2020s}, journal = {CoRR}, volume = {abs/2201.03545}, year = {2022}, url = {https://arxiv.org/abs/2201.03545}, eprinttype = {arXiv}, eprint = {2201.03545}, timestamp = {Thu, 20 Jan 2022 14:21:35 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-03545.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }