许可协议: apache-2.0
标签:

• 视觉
• 图像分类
  数据集:
• imagenet-21k
  微件示例:
• 图片链接: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
  示例标题: 老虎
• 图片链接: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
  示例标题: 茶壶
• 图片链接: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
  示例标题: 宫殿

ConvNeXT (大尺寸模型)

该ConvNeXT模型在ImageNet-22k数据集上以224x224分辨率训练而成，由Liu等人在论文《A ConvNet for the 2020s》中提出，并首次发布于此代码库。

免责声明：发布ConvNeXT的团队未为此模型编写说明卡片，本卡片由Hugging Face团队撰写。

模型描述

ConvNeXT是一个纯卷积模型（ConvNet），受视觉Transformer设计启发，宣称性能超越Transformer。作者以ResNet为基础，借鉴Swin Transformer的理念对其进行了"现代化"改造。

用途与限制

您可将该原始模型用于图像分类任务。访问模型中心寻找针对特定任务微调的版本。

使用方法

以下示例展示如何将COCO 2017数据集的图像分类为ImageNet 1000个类别之一：

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")  
model = ConvNextForImageClassification.from_pretrained("facebook/convnext-large-224-22k")  

inputs = feature_extractor(image, return_tensors="pt")  

with torch.no_grad():  
    logits = model(**inputs).logits  

# 模型预测22k个ImageNet类别之一  
predicted_label = logits.argmax(-1).item()  
print(model.config.id2label[predicted_label])  

更多代码示例请参阅文档。

引用信息

@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}  
}