模型:
facebook/convnextv2-nano-22k-224
ConvNeXt V2是使用FCMAE框架进行预训练,并在ImageNet-22K数据集上进行了调优的模型,分辨率为224x224。该模型在Woo等人的论文 ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders 中被介绍,并于 this repository 首次发布。
免责声明:发布ConvNeXT V2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。
ConvNeXt V2是一种纯卷积模型(ConvNet),引入了全卷积蒙版自编码器框架(FCMAE)和ConvNeXt的新型全局响应归一化(GRN)层。ConvNeXt V2在各种识别基准上显著提高了纯卷积网络的性能。
您可以使用原始模型进行图像分类。请参阅 model hub ,以查找您感兴趣的任务的精调版本。
以下是使用此模型将COCO 2017数据集中的图像分类为1,000个ImageNet类别之一的步骤:
from transformers import AutoImageProcessor, ConvNextV2ForImageClassification import torch from datasets import load_dataset dataset = load_dataset("huggingface/cats-image") image = dataset["test"]["image"][0] preprocessor = AutoImageProcessor.from_pretrained("facebook/convnextv2-nano-22k-224") model = ConvNextV2ForImageClassification.from_pretrained("facebook/convnextv2-huge-22k-224") inputs = preprocessor(image, return_tensors="pt") with torch.no_grad(): logits = model(**inputs).logits # model predicts one of the 1000 ImageNet classes predicted_label = logits.argmax(-1).item() print(model.config.id2label[predicted_label]),
对于更多代码示例,请参考 documentation 。
@article{DBLP:journals/corr/abs-2301-00808, author = {Sanghyun Woo and Shoubhik Debnath and Ronghang Hu and Xinlei Chen and Zhuang Liu and In So Kweon and Saining Xie}, title = {ConvNeXt {V2:} Co-designing and Scaling ConvNets with Masked Autoencoders}, journal = {CoRR}, volume = {abs/2301.00808}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2301.00808}, doi = {10.48550/arXiv.2301.00808}, eprinttype = {arXiv}, eprint = {2301.00808}, timestamp = {Tue, 10 Jan 2023 15:10:12 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2301-00808.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }