vit_base_patch8_224.augreg2_in21k_ft_in1k的模型卡片

这是一个视觉Transformer（ViT）图像分类模型。由论文作者在ImageNet-21k上进行训练，并由Ross Wightman在ImageNet-1k上进行了额外的数据增强和正则化（重新）微调。

模型细节

• 模型类型：图像分类 / 特征骨干
• 模型统计信息：
  • 参数数目（百万）：86.6
  • GMACs：66.9
  • 激活次数（百万）：65.7
  • 图像尺寸：224 x 224
• 论文：
  • 如何训练您的ViT？视觉Transformer中的数据、增强和正则化： https://arxiv.org/abs/2106.10270
  • 一幅图像等于16x16个单词：大规模图像识别的Transformer： https://arxiv.org/abs/2010.11929v2
• 数据集：ImageNet-1k
• 预训练数据集：ImageNet-21k
• 原始论文： https://github.com/google-research/vision_transformer

模型用途

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.augreg2_in21k_ft_in1k', 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_base_patch8_224.augreg2_in21k_ft_in1k',
    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, 785, 768) shaped tensor

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

模型比较

在timm中探索该模型的数据集和运行时指标 model results 。

引用

@article{steiner2021augreg,
  title={How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers},
  author={Steiner, Andreas and Kolesnikov, Alexander and and Zhai, Xiaohua and Wightman, Ross and Uszkoreit, Jakob and Beyer, Lucas},
  journal={arXiv preprint arXiv:2106.10270},
  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}}
}