paperClub-hub/chinese_clip
中文CLIP：自定义数据集，可根据文图提取向量，实现文图匹配。
This tool helps you organize and find Chinese text and images more efficiently. You provide your own collection of Chinese images and corresponding text descriptions, and it processes them to create unique numerical representations (vectors). These vectors allow you to quickly find images using text queries, or vice-versa, making it easier to manage large multimedia datasets. This is ideal for anyone working with large volumes of Chinese visual and textual content, such as content managers, e-commerce specialists, or researchers.
No commits in the last 6 months.
Use this if you need to build a custom search system or recommendation engine for Chinese images and text using your specific dataset.
Not ideal if you are looking for a pre-trained model for non-Chinese languages or if you do not have your own specialized dataset for training.
Stars
22
Forks
4
Language
Python
License
—
Category
Last pushed
Sep 14, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/paperClub-hub/chinese_clip"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unum-cloud/UForm
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts,...
rom1504/clip-retrieval
Easily compute clip embeddings and build a clip retrieval system with them
mazzzystar/Queryable
Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.
s-emanuilov/litepali
LitePali is a minimal, efficient implementation of ColPali for image retrieval and indexing,...
slavabarkov/tidy
Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized...