许可协议: apache-2.0
库名称: timm
标签:

• 图像特征提取
• timm
• transformers
  数据集:
• imagenet-21k

模型卡片: vit_base_patch32_224.orig_in21k

一个基于Vision Transformer (ViT)的图像分类模型。由论文作者在ImageNet-21k上使用JAX预训练，后由Ross Wightman移植到PyTorch。该模型不包含分类头，适用于特征提取和微调场景。

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(M): 87.5
  • 计算量(GMACs): 4.4
  • 激活值(M): 4.2
  • 图像尺寸: 224 x 224
• 相关论文:
  • 《An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale》: https://arxiv.org/abs/2010.11929v2
• 数据集: ImageNet-21k
• 原始实现: https://github.com/google-research/vision_transformer

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_patch32_224.orig_in21k', 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_patch32_224.orig_in21k',  
    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(batch_size, num_features)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，形状为(1, 50, 768)的张量  

output = model.forward_head(output, pre_logits=True)  
# 输出为(1, num_features)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{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}}  
}