vit_base_patch16_rpn_224.sw_in1k模型卡片

Vision Transformer (ViT) 图像分类模型。这是一个由 residual post normalization blocks 组成的 timm 特定变体的架构。使用以下 timm 中的模板，基于 ImageNet-1k 在 timm 中进行训练。

训练细节:

• 基于 Swin Transformer train / pretrain 的训练配方，并进行了修改 (与 DeiT 和 ConvNeXt 配方相关)
• AdamW 优化器，梯度裁剪，EMA 权重平均化
• 使用余弦学习率调度进行预热

模型细节

• 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): 86.5
  • GMACs: 16.8
  • 激活数量 (百万): 16.4
  • 图像大小: 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 个词: 图像大规模识别的 Transformer: https://arxiv.org/abs/2010.11929v2
• 数据集: ImageNet-1k
• 原始资料: 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_base_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_base_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, 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}
}