许可协议：apache-2.0
库名称：timm
标签：

• 图像特征提取
• timm
• transformers

vit_small_patch14_reg4_dinov2.lvd142m 模型卡

一种带有寄存器的视觉Transformer（ViT）图像特征模型。采用自监督DINOv2方法在LVD-142M数据集上预训练。

模型详情

• 模型类型： 图像分类/特征主干网络
• 模型统计：
  • 参数量（百万）：22.1
  • GMACs：29.6
  • 激活量（百万）：57.5
  • 图像尺寸：518 x 518
• 相关论文：
  • 《视觉Transformer需要寄存器》：https://arxiv.org/abs/2309.16588
  • 《DINOv2：无需监督学习鲁棒视觉特征》：https://arxiv.org/abs/2304.07193
  • 《一张图像等于16x16个词：大规模图像识别的Transformer》：https://arxiv.org/abs/2010.11929v2
• 原始实现： https://github.com/facebookresearch/dinov2
• 预训练数据集： LVD-142M

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_small_patch14_reg4_dinov2.lvd142m', pretrained=True)  
model = model.eval()  

# 获取模型特定的变换（归一化、调整大小）  
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_small_patch14_reg4_dinov2.lvd142m',  
    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、调整大小）  
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))  
# 输出未池化，为（1，1374，384）形状的张量  

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

@article{darcet2023vision,  
  title={Vision Transformers Need Registers},  
  author={Darcet, Timoth{'e}e and Oquab, Maxime and Mairal, Julien and Bojanowski, Piotr},  
  journal={arXiv preprint arXiv:2309.16588},  
  year={2023}  
}  

@misc{oquab2023dinov2,  
  title={DINOv2: Learning Robust Visual Features without Supervision},  
  author={Oquab, Maxime and Darcet, Timothée and Moutakanni, Theo and Vo, Huy V. and Szafraniec, Marc and Khalidov, Vasil and Fernandez, Pierre and Haziza, Daniel and Massa, Francisco and El-Nouby, Alaaeldin and Howes, Russell and Huang, Po-Yao and Xu, Hu and Sharma, Vasu and Li, Shang-Wen and Galuba, Wojciech and Rabbat, Mike and Assran, Mido and Ballas, Nicolas and Synnaeve, Gabriel and Misra, Ishan and Jegou, Herve and Mairal, Julien and Labatut, Patrick and Joulin, Armand and Bojanowski, Piotr},  
  journal={arXiv:2304.07193},  
  year={2023}  
}  

@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}}  
}