vit_relpos_medium_patch16_cls_224.sw_in1k模型卡片

一个Vision Transformer（ViT）图像分类模型。这是timm中ViT架构的特定变种，具有相对位置嵌入、类令牌和通过类令牌的最终表示方式。在timm中使用下面描述的模板对ImageNet-1k进行训练。

模型详细信息：

• 基于Swin Transformer的训练/预训练模板进行修改（涉及到DeiT和ConvNeXt模板）
• AdamW优化器、梯度剪裁、EMA权重平均
• 余弦学习率衰减策略（带warmup）

模型详情

• 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）：38.8
  • GMACs：7.5
  • 激活数量（百万）：13.3
  • 图像尺寸：224 x 224
• 相关论文：
  • Swin Transformer V2: 扩展容量与分辨率: https://arxiv.org/abs/2111.09883
  • 一张图片相当于16x16个单词：大规模图像识别中的Transformer: https://arxiv.org/abs/2010.11929v2
• 数据集：ImageNet-1k
• 原始论文： https://github.com/huggingface/pytorch-image-models

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_relpos_medium_patch16_cls_224.sw_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_relpos_medium_patch16_cls_224.sw_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, 197, 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}}
}

@inproceedings{liu2021swinv2,
  title={Swin Transformer V2: Scaling Up Capacity and Resolution}, 
  author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
  booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2022}
}

@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}
}