许可协议：apache-2.0
库名称：timm
标签：

• 图像特征提取
• timm
• transformers

vit_base_patch8_224.dino 模型卡

基于自监督DINO方法训练的视觉Transformer（ViT）图像特征模型。

模型详情

• 模型类型： 图像分类/特征骨干网络
• 模型统计：
  • 参数量（百万）：85.8
  • GMACs：66.9
  • 激活量（百万）：65.7
  • 图像尺寸：224 x 224
• 相关论文：
  • 《自监督视觉Transformer的新兴特性》：https://arxiv.org/abs/2104.14294
  • 《一张图像等价于16x16个单词：大规模图像识别的Transformer应用》：https://arxiv.org/abs/2010.11929v2
• 预训练数据集： ImageNet-1k
• 原始实现： https://github.com/facebookresearch/dino

模型使用

图像分类

from urllib.request import urlopen  
from PIL import Image  
import timm  

img = Image.open(urlopen(  
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'  
))  

model = timm.create_model('vit_base_patch8_224.dino', pretrained=True)  
model = model.eval()  

# 获取模型特定的变换（归一化、调整尺寸）  
data_config = timm.data.resolve_model_data_config(model)  
transforms = timm.data.create_transform(**data_config, is_training=False)  

output = model(transforms(img).unsqueeze(0))  # 将单张图像扩展为批次大小为1  

top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)  

图像嵌入

from urllib.request import urlopen  
from PIL import Image  
import timm  

img = Image.open(urlopen(  
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'  
))  

model = timm.create_model(  
    'vit_base_patch8_224.dino',  
    pretrained=True,  
    num_classes=0,  # 移除分类器nn.Linear  
)  
model = model.eval()  

# 获取模型特定的变换（归一化、调整尺寸）  
data_config = timm.data.resolve_model_data_config(model)  
transforms = timm.data.create_transform(**data_config, is_training=False)  

output = model(transforms(img).unsqueeze(0))  # 输出为（批次大小，特征数）形状的张量  

# 或等效方式（无需设置num_classes=0）  

output = model.forward_features(transforms(img).unsqueeze(0))  
# 输出为非池化形式，形状为（1, 785, 768）的张量  

output = model.forward_head(output, pre_logits=True)  
# 输出为（1, 特征数）形状的张量  

模型比较

在timm的模型结果中探索该模型的数据集和运行时指标。

引用

@inproceedings{caron2021emerging,  
  title={Emerging properties in self-supervised vision transformers},  
  author={Caron, Mathilde and Touvron, Hugo and Misra, Ishan and J{'e}gou, Herv{'e} and Mairal, Julien and Bojanowski, Piotr and Joulin, Armand},  
  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},  
  pages={9650--9660},  
  year={2021}  
}  

@article{dosovitskiy2020vit,  
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},  
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},  
  journal={ICLR},  
  year={2021}  
}  

@misc{rw2019timm,  
  author = {Ross Wightman},  
  title = {PyTorch Image Models},  
  year = {2019},  
  publisher = {GitHub},  
  journal = {GitHub repository},  
  doi = {10.5281/zenodo.4414861},  
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}  
}