Vit B 16 SigLIP2 512

🚀 ViT-B-16-SigLIP2-512模型卡片

本項目是一個基於WebLI數據集訓練的SigLIP 2視覺語言模型，可用於零樣本圖像分類任務。該模型從原始的JAX檢查點轉換而來，適用於OpenCLIP庫。

🚀 快速開始

環境準備

確保你的環境滿足以下依賴要求：

• open-clip-torch >= 2.31.0
• timm >= 1.0.15

代碼示例

import torch
import torch.nn.functional as F
from urllib.request import urlopen
from PIL import Image
from open_clip import create_model_from_pretrained, get_tokenizer # works on open-clip-torch >= 2.31.0, timm >= 1.0.15

model, preprocess = create_model_from_pretrained('hf-hub:timm/ViT-B-16-SigLIP2-512')
tokenizer = get_tokenizer('hf-hub:timm/ViT-B-16-SigLIP2-512')

image = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
image = preprocess(image).unsqueeze(0)

labels_list = ["a dog", "a cat", "a donut", "a beignet"]
text = tokenizer(labels_list, context_length=model.context_length)

with torch.no_grad(), torch.cuda.amp.autocast():
    image_features = model.encode_image(image, normalize=True)
    text_features = model.encode_text(text, normalize=True)
    text_probs = torch.sigmoid(image_features @ text_features.T * model.logit_scale.exp() + model.logit_bias)

zipped_list = list(zip(labels_list, [100 * round(p.item(), 3) for p in text_probs[0]]))
print("Label probabilities: ", zipped_list)

✨ 主要特性

• 基於WebLI數據集訓練的SigLIP 2視覺語言模型。
• 支持零樣本圖像分類任務。
• 從原始的JAX檢查點轉換而來，可在OpenCLIP中使用。

📦 安裝指南

文檔未提及具體安裝步驟，可參考依賴庫的官方文檔進行安裝：

• open-clip-torch：open-clip-torch官方倉庫
• timm：timm官方倉庫

📚 詳細文檔

模型詳情

• 模型類型：對比圖像文本、零樣本圖像分類。
• 原始倉庫：https://github.com/google-research/big_vision
• 訓練數據集：WebLI
• 相關論文：
  • SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
  • Sigmoid loss for language image pre-training

引用信息

@article{tschannen2025siglip,
  title={SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features},
  author={Tschannen, Michael and Gritsenko, Alexey and Wang, Xiao and Naeem, Muhammad Ferjad and Alabdulmohsin, Ibrahim and Parthasarathy, Nikhil and Evans, Talfan and Beyer, Lucas and Xia, Ye and Mustafa, Basil and H'enaff, Olivier and Harmsen, Jeremiah and Steiner, Andreas and Zhai, Xiaohua},
  year={2025},
  journal={arXiv preprint arXiv:2502.14786}
}        

@article{zhai2023sigmoid,
  title={Sigmoid loss for language image pre-training},
  author={Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas},
  journal={arXiv preprint arXiv:2303.15343},
  year={2023}
}

@misc{big_vision,
  author = {Beyer, Lucas and Zhai, Xiaohua and Kolesnikov, Alexander},
  title = {Big Vision},
  year = {2022},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/google-research/big_vision}}
}

📄 許可證

本項目採用Apache-2.0許可證。