许可协议: cc-by-nc-4.0 库名称: timm 标签:

• 图像特征提取
• timm
• transformers

vit_huge_patch14_224.mae 模型卡片

一个基于视觉Transformer（ViT）的图像特征模型。采用自监督掩码自编码器（MAE）方法在ImageNet-1k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）: 630.8
  • 计算量（GMACs）: 167.4
  • 激活值（百万）: 139.4
  • 图像尺寸: 224 x 224 像素
• 相关论文:
  • 《掩码自编码器是可扩展的视觉学习者》: https://arxiv.org/abs/2111.06377
  • 《一张图像等价于16x16个单词：大规模图像识别的Transformer模型》: https://arxiv.org/abs/2010.11929v2
• 预训练数据集: ImageNet-1k
• 原始实现: https://github.com/facebookresearch/mae

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_huge_patch14_224.mae', pretrained=True)
model = model.eval()

# 获取模型特定的变换（归一化、尺寸调整）
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_huge_patch14_224.mae',
    pretrained=True,
    num_classes=0,  # 移除分类器nn.Linear层
)
model = model.eval()

# 获取模型特定的变换（归一化、尺寸调整）
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，特征维度）形状的张量

# 或等效操作（无需设置num_classes=0）

output = model.forward_features(transforms(img).unsqueeze(0))
# 输出为非池化结果，形状为（1，257，1280）的张量

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

模型对比

在timm的模型结果中查看该模型的数据集和运行时指标。

引用文献

@Article{MaskedAutoencoders2021,
  author  = {Kaiming He and Xinlei Chen and Saining Xie and Yanghao Li and Piotr Doll{'a}r and Ross Girshick},
  journal = {arXiv:2111.06377},
  title   = {Masked Autoencoders Are Scalable Vision Learners},
  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}}
}