Japanese Clip Vit B 16

🚀 rinna/japanese-clip-vit-b-16

这是由rinna株式会社训练的日语CLIP（对比语言 - 图像预训练）模型。

如需了解其他可用模型，请参阅 japanese-clip。

🚀 快速开始

安装包

$ pip install git+https://github.com/rinnakk/japanese-clip.git

运行代码

import io
import requests
from PIL import Image
import torch
import japanese_clip as ja_clip

device = "cuda" if torch.cuda.is_available() else "cpu"

model, preprocess = ja_clip.load("rinna/japanese-clip-vit-b-16", cache_dir="/tmp/japanese_clip", device=device)
tokenizer = ja_clip.load_tokenizer()

img = Image.open(io.BytesIO(requests.get('https://images.pexels.com/photos/2253275/pexels-photo-2253275.jpeg?auto=compress&cs=tinysrgb&dpr=3&h=750&w=1260').content))
image = preprocess(img).unsqueeze(0).to(device)
encodings = ja_clip.tokenize(
    texts=["犬", "猫", "象"],
    max_seq_len=77,
    device=device,
    tokenizer=tokenizer, # this is optional. if you don't pass, load tokenizer each time
)

with torch.no_grad():
    image_features = model.get_image_features(image)
    text_features = model.get_text_features(**encodings)
    
    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs)  # prints: [[1.0, 0.0, 0.0]]

🔧 技术细节

模型架构

该模型使用ViT - B/16 Transformer架构作为图像编码器，并使用12层BERT作为文本编码器。图像编码器是从AugReg vit - base - patch16 - 224模型初始化而来的。

训练数据

该模型在CC12M上进行训练，其字幕已被翻译成日语。

📄 许可证

Apache 2.0许可证

📅 发布日期

2022年5月12日

📚 引用方式

@misc{rinna-japanese-clip-vit-b-16,
    title = {rinna/japanese-clip-vit-b-16},
    author = {Shing, Makoto and Zhao, Tianyu and Sawada, Kei},
    url = {https://huggingface.co/rinna/japanese-clip-vit-b-16}
}

@inproceedings{sawada2024release,
    title = {Release of Pre-Trained Models for the {J}apanese Language},
    author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
    booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
    month = {5},
    year = {2024},
    pages = {13898--13905},
    url = {https://aclanthology.org/2024.lrec-main.1213},
    note = {\url{https://arxiv.org/abs/2404.01657}}
}