vit_relpos_medium_patch16_rpn_224.sw_in1k 模型卡片

一种视觉Transformer（ViT）图像分类模型。这是ViT架构的timmm特定变体，具有相对位置嵌入和残差后归一化块，无类别令牌，并通过全局平均池化进行最终表示。使用下述timmm的ImageNet-1k训练模型的模板。

运行细节:

• 基于Swin Transformer的训练/预训练方式，并进行了修改（涉及到DeiT和ConvNeXt的方式）
• AdamW优化器，梯度裁剪，EMA权重平均化
• 随着预热的余弦LR调度方式

模型细节

• 模型类型: 图像分类/特征骨干
• 模型统计数据:
  • 参数数目（M）: 38.7
  • GMACs: 7.5
  • 激活数目（M）: 12.1
  • 图像尺寸: 224 x 224
• 论文:
  • Swin Transformer V2: 扩展容量和分辨率: https://arxiv.org/abs/2111.09883
  • 一张图值得16x16个单词: 图像识别的Transformer规模化方法: 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_rpn_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_rpn_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, 196, 512) shaped tensor

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

模型对比

在timm model results 中探索此模型的数据集和运行时度量。

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}
}