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。
☆22Updated 2 years ago
Alternatives and similar repositories for chinese_clip:
Users that are interested in chinese_clip are comparing it to the libraries listed below
- 计算机视觉课程设计-基于Chinese-CLIP的图文检索系统☆54Updated last year
- 基于多模态检索的互联网图文匹配☆12Updated 10 months ago
- 人工智能实验五:多模态情感分类☆14Updated 2 years ago
- 基于ClipCap的看图说话Image Caption模型☆294Updated 2 years ago
- ☆13Updated last year
- 商品图像检索、多模态、深度学习☆31Updated 3 years ago
- DIP & NLP期末大作业 — 课程设计☆18Updated 2 years ago
- ☆32Updated 2 years ago
- 模式识别课设代码:图文生成(CLIP+DALLE+BriVL)☆21Updated last year
- Building a VLM model starts from the basic module.☆11Updated 9 months ago
- CLIP中文encoder☆22Updated 2 years ago
- 使用pytorch完成的一个多模态分类任务,文本和图像部分分别使用了bert和resnet提取特征(在config里可以组合多种模型),在我的小规模数据集上取得了良好的性能(验证集acc96%)☆70Updated last year
- ☆15Updated 10 months ago
- 多模态视频分类模型☆17Updated 2 years ago
- 抽取式NLP模型(阅读理解模型,MRC)实现词义消歧(WSD)☆12Updated 2 years ago
- 该项目旨在通过输入文本描述来检索与之相匹配的图片。☆31Updated last year
- transformers结构的中文OFA模型☆123Updated last year
- 补充了一些Visualglm缺少的文件,可以对Visualglm进行训练,实例中是对人脸做了面相的识别☆13Updated last year
- 一个多模态内容理解算法框架,其中包含数据处理、预训练模型、常见模型以及模型加速等模块。☆307Updated 3 years ago
- 基于pytorch+bilstm_crf的中文命名实体识别☆14Updated 2 years ago
- 中文领域的多模态Bert☆46Updated 4 years ago
- Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.☆166Updated 2 years ago
- Workshop on Foundation Model 1st foundation model challenge Track1 codebase (Open TransMind v1.0)☆18Updated last year
- 基于Bilstm + CRF的信息抽取模型☆32Updated 3 years ago
- 基于pytorch+bert的中文文本分类☆81Updated last year
- 使用bert进行中文方面级情感识别。☆22Updated last year
- Chinese CLIP models with SOTA performance.☆53Updated last year
- Mimix: A Text Generation Tool and Pretrained Chinese Models☆155Updated 3 months ago
- VLE: Vision-Language Encoder (VLE: 视觉-语言多模态预训练模型)☆186Updated last year
- BLOOM 模型的指令微调☆24Updated last year