#87 · Primary category： Computer Vision
Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
Project last updated：03/31/26
GitHub Stars
6.0K
Forks
552
Contributors
11
License
MIT
Why we included this project
Teams building products that pair Chinese text with images, such as search over product catalogs or photo libraries, often start with Chinese-CLIP. The project provides image and text encoders trained on about 200 million Chinese image-text pairs, so you can compute feature similarity and run cross-modal retrieval without assembling your own training data. It also supports zero-shot image classification, where you simply name the candidate labels in Chinese. Along with the ready-to-use inference API, the repo includes training and fine-tuning code, letting you adapt the model to your own domain data. Conversion scripts for ONNX, TensorRT, and CoreML make it practical to move the model into real deployments, and the Hugging Face transformers integration keeps it easy to slot into existing pipelines.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)