Vit L16 Mim

🚀 vit_l16_mim模型卡

这是一个使用掩码图像建模（MIM）预训练的ViT - L16图像编码器。该模型未针对特定分类任务进行微调，旨在用作通用特征提取器或用于下游任务（如目标检测、分割或自定义分类）的主干网络。

🚀 快速开始

此模型可作为通用特征提取器或下游任务的主干网络，以下是使用示例。

✨ 主要特性

• 基于掩码图像建模（MIM）进行预训练，具有强大的特征提取能力。
• 未针对特定分类任务微调，通用性强，可灵活应用于多种下游任务。

📚 详细文档

模型详情

💻 使用示例

基础用法

import torch
import birder
from PIL import Image

(net, model_info) = birder.load_pretrained_model("vit_l16_mim_400", inference=True)

# Get the image size the model was trained on
size = birder.get_size_from_signature(model_info.signature)

# Create an inference transform
transform = birder.classification_transform(size, model_info.rgb_stats)

image = Image.open("path/to/image.jpeg")
input_tensor = transform(image).unsqueeze(dim=0)
with torch.inference_mode():
    embedding = net.embedding(input_tensor)
    # embedding is a tensor with shape of (1, 1024)

📄 许可证

本项目采用Apache - 2.0许可证。

📚 引用

@misc{dosovitskiy2021imageworth16x16words,
      title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
      author={Alexey Dosovitskiy and Lucas Beyer and Alexander Kolesnikov and Dirk Weissenborn and Xiaohua Zhai and Thomas Unterthiner and Mostafa Dehghani and Matthias Minderer and Georg Heigold and Sylvain Gelly and Jakob Uszkoreit and Neil Houlsby},
      year={2021},
      eprint={2010.11929},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2010.11929},
}

@misc{he2021maskedautoencodersscalablevision,
      title={Masked Autoencoders Are Scalable Vision Learners},
      author={Kaiming He and Xinlei Chen and Saining Xie and Yanghao Li and Piotr Dollár and Ross Girshick},
      year={2021},
      eprint={2111.06377},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2111.06377},
}