Eva02 Base Patch14 224.mim In22k

🚀 eva02_base_patch14_224.mim_in22k模型卡片

這是一個EVA02特徵/表徵模型。由論文作者使用掩碼圖像建模（以EVA - CLIP作為MIM教師）在ImageNet - 22k上進行預訓練。

EVA - 02模型是帶有均值池化、SwiGLU、旋轉位置嵌入（ROPE）以及在MLP中使用額外LN（針對Base和Large版本）的視覺變換器。

注意：為了與其他模型保持一致，timm檢查點採用float32格式。在某些情況下，原始檢查點為float16或bfloat16，如果有此需求，請查看原始版本。

✨ 主要特性

• 模型類型：圖像分類/特徵主幹
• 模型統計信息：
  • 參數數量（M）：85.8
  • GMACs：23.2
  • 激活值（M）：36.6
  • 圖像尺寸：224 x 224
• 相關論文：
  • 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
• 原始資源：
  • https://github.com/baaivision/EVA
  • https://huggingface.co/Yuxin - CV/EVA - 02
• 預訓練數據集：ImageNet - 22k

📦 安裝指南

文檔中未提及安裝步驟，若需使用eva02_base_patch14_224.mim_in22k模型，可參考timm庫的安裝方式，一般可使用以下命令：

pip install timm

💻 使用示例

基礎用法

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)

高級用法

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

📚 詳細文檔

可在timm 模型結果中查看該模型的數據集和運行時指標。

模型對比

📄 許可證

本項目採用MIT許可證。

📖 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}}
}