Eva02 Base Patch14 224.mim In22k

🚀 eva02_base_patch14_224.mim_in22k模型卡片

这是一个EVA02特征/表征模型。由论文作者使用掩码图像建模（以EVA - CLIP作为MIM教师）在ImageNet - 22k上进行预训练。

EVA - 02模型是带有均值池化、SwiGLU、旋转位置嵌入（ROPE）以及在MLP中使用额外LN（针对Base和Large版本）的视觉变换器。

注意：为了与其他模型保持一致，timm检查点采用float32格式。在某些情况下，原始检查点为float16或bfloat16，如果有此需求，请查看原始版本。

✨ 主要特性

• 模型类型：图像分类/特征主干
• 模型统计信息：
  • 参数数量（M）：85.8
  • GMACs：23.2
  • 激活值（M）：36.6
  • 图像尺寸：224 x 224
• 相关论文：
  • EVA - 02: A Visual Representation for Neon Genesis: https://arxiv.org/abs/2303.11331
  • EVA - CLIP: Improved Training Techniques for CLIP at Scale: https://arxiv.org/abs/2303.15389
• 原始资源：
  • https://github.com/baaivision/EVA
  • https://huggingface.co/Yuxin - CV/EVA - 02
• 预训练数据集：ImageNet - 22k

📦 安装指南

文档中未提及安装步骤，若需使用eva02_base_patch14_224.mim_in22k模型，可参考timm库的安装方式，一般可使用以下命令：

pip install timm

💻 使用示例

基础用法

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('eva02_base_patch14_224.mim_in22k', 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)

高级用法

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(
    'eva02_base_patch14_224.mim_in22k',
    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, 257, 768) shaped tensor

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

📚 详细文档

可在timm 模型结果中查看该模型的数据集和运行时指标。

模型对比

📄 许可证

本项目采用MIT许可证。

📖 引用信息

@article{EVA02,
  title={EVA-02: A Visual Representation for Neon Genesis},
  author={Fang, Yuxin and Sun, Quan and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
  journal={arXiv preprint arXiv:2303.11331},
  year={2023}
}

@article{EVA-CLIP,
  title={EVA-02: A Visual Representation for Neon Genesis},
  author={Sun, Quan and Fang, Yuxin and Wu, Ledell and Wang, Xinlong and Cao, Yue},
  journal={arXiv preprint arXiv:2303.15389},
  year={2023}
}

@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}}
}