vit_medium_patch16_gap_256.sw_in12k_ft_in1k的模型卡片

一种视觉变换器（ViT）图像分类模型。这是一个特定的timm架构变体，具有令牌全局平均池化。在timm中，使用下面描述的配方模板在ImageNet-12k上进行预训练，并在ImageNet-1k上进行微调。

配方细节：

• 基于Swin Transformer的训练/预训练配方，带有修改（与DeiT和ConvNeXt的配方相关）
• AdamW优化器，梯度裁剪，EMA权重平均
• 余弦LR计划与预热

模型细节

• 模型类型：图像分类/特征骨干
• 模型统计：
  • 参数数目（M）：38.9
  • GMACs：9.8
  • 激活函数数目（M）：14.3
  • 图像大小：256 x 256
• 论文：
  • 一张图片值得16x16个单词：用于图像识别的变换器规模上的变换器： https://arxiv.org/abs/2010.11929v2
• 数据集：ImageNet-1k
• 预训练数据集：ImageNet-12k
• 原始： https://github.com/huggingface/pytorch-image-models

模型用法

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_medium_patch16_gap_256.sw_in12k_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_medium_patch16_gap_256.sw_in12k_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, 256, 512) shaped tensor

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

模型比较

在timm中探索此模型的数据集和运行时指标： model results

引用

@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}}
}

@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}
}