Chinese-CLIP
Chinese CLIP
A deep learning framework for cross-modal retrieval and representation generation using large-scale Chinese datasets
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
5k stars
37 watching
479 forks
Language: Python
last commit: 7 months ago
Linked from 1 awesome list
chineseclipcomputer-visioncontrastive-losscoreml-modelsdeep-learningimage-text-retrievalmulti-modalmulti-modal-learningnlppretrained-modelspytorchtransformersvision-and-language-pre-trainingvision-language
crownpku/awesome-chinese-nlpRelated projects:
| Repository | Description | Stars |
|---|---|---|
 nvlabs/ffhq-dataset | A high-quality image dataset of human faces created to benchmark generative adversarial networks. | 3,776 |
 tencentarc-qq/qa-clip | Provides Chinese language models with high performance for image-text retrieval and classification tasks. | 51 |
 acccccccb/vue-img-cutter | An image cropping plugin for Vue.js applications | 496 |
 openai/clip | A neural network trained on image and text pairs to predict the most relevant text snippet given an image | 26,460 |
 tencentarc/gfpgan | An algorithm for restoring damaged or obscured faces in images | 36,009 |
 rom1504/clip-retrieval | A tool for efficiently computing and utilizing CLIP embeddings for semantic search in multimodal data | 2,440 |
 aaronshan/12306-captcha | Deep learning-based system to recognize and classify 12306 captcha images | 281 |
 996refuse/zheye | A Python-based OCR system designed to recognize handwritten Chinese characters in vertical captcha images | 800 |
 yongliang-wu/explorecfg | This project develops strategies to optimize in-context sequence configurations for Vision-Language few-shot learning, with a focus on exploring the effects of varying configurations on image-text pairs. | 33 |
 wanshun123/facial-beauty-prediction | Web application that predicts facial beauty ratings from uploaded selfies using machine learning on a specific dataset. | 10 |
 dog-qiuqiu/ultralight-simplepose | A lightweight human body posture key point model using computer vision and deep learning techniques. | 302 |
 jin-s13/coco-wholebody | A large-scale benchmark and dataset for whole-body pose estimation in images | 770 |
 sczhou/codeformer | A deep learning-based framework for enhancing and restoring images of faces in various conditions | 16,049 |
 soloice/chinese-character-recognition | This project demonstrates how to build and train a convolutional neural network (CNN) to recognize Chinese characters. | 200 |
 cszn/ircnn | This project trains deep CNN denoisers to improve image restoration tasks such as deblurring and demosaicking through model-based optimization methods. | 602 |