Vit Large Patch16 224.orig In21k

🚀 vit_large_patch16_224.orig_in21k模型卡片

这是一个视觉变换器（ViT）图像分类模型。由论文作者在JAX中基于ImageNet - 21k数据集进行预训练，再由Ross Wightman将其移植到PyTorch。该模型没有分类头，仅适用于特征提取和微调。

🚀 快速开始

本模型可用于图像分类和提取图像嵌入特征，具体使用方法见下方使用示例。

✨ 主要特性

• 模型类型：图像分类/特征骨干网络
• 模型统计信息：
  • 参数数量（百万）：303.3
  • 吉兆次乘法累加运算（GMACs）：59.7
  • 激活值数量（百万）：43.8
  • 图像尺寸：224 x 224
• 相关论文：
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• 数据集：ImageNet - 21k
• 原始代码库：https://github.com/google-research/vision_transformer

📦 安装指南

文档未提及安装步骤，可参考timm库的官方安装说明进行安装。

💻 使用示例

基础用法

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_large_patch16_224.orig_in21k', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
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))  # unsqueeze single image into batch of 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_large_patch16_224.orig_in21k',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()

# get model specific transforms (normalization, resize)
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))  # output is (batch_size, num_features) shaped tensor

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 197, 1024) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor

📚 详细文档

可在timm的模型结果页面中查看该模型的数据集和运行时指标。

📄 许可证

本模型采用Apache - 2.0许可证。

📚 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}}
}