sugarandgugu / Text2Image-Retrieval
计算机视觉课程设计-基于Chinese-CLIP的图文检索系统
☆61Updated last year
Alternatives and similar repositories for Text2Image-Retrieval:
Users that are interested in Text2Image-Retrieval are comparing it to the libraries listed below
- 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
- 该项目旨在通过输入文本描述来检索与之相匹配的图片。☆37Updated last year
- 基于多模态检索的互联网图文匹配☆13Updated last year
- 毕业设计:《基于CLIP模型的视频文本检索设计与实现》☆11Updated 8 months ago
- 基于ClipCap的看图说话Image Caption模型☆300Updated 3 years ago
- 多模态视频分类模型☆20Updated 2 years ago
- 使用OpenCV+onnxruntime部署中文clip做以文搜图,给出一句话来描述想要的图片,就能从图库中搜出来符合要求的图片。包含C++和Python两个版本的程序☆72Updated last year
- 2024.06.19 本项目使用Chinese-CLIP搭建文搜图/图搜图页面,旨在帮助用户快速使用跨模态检索任务。本项目代码针对MUGE数据集约19w(189585张)数据作为底库数据。本项目提供了提取特征, 检索, 以及uI代码。☆15Updated 9 months ago
- 这是一个clip-pytorch的模型,可以训练自己的数据集。☆222Updated 2 years ago
- DIP & NLP期末大作业 — 课程设计☆18Updated 2 years ago
- 一些大语言模型和多模态模型的应用,主要包括Rag,小模型,Agent,跨模态搜索,OCR等等☆161Updated 5 months ago
- 中文CLIP预训练模型☆410Updated 2 years ago
- WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge☆120Updated 5 months 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%)☆77Updated 2 years ago
- VLE: Vision-Language Encoder (VLE: 视觉-语言多模态预训练模型)☆190Updated 2 years ago
- Train a model for Image Caption from ViT and GPT pretrained model☆17Updated 2 years ago
- A project that can generate ancient poems based on pictures, including CLIP, T5, GPT2 models☆21Updated 2 months ago
- 模型 llava-Qwen2-7B-Instruct-Chinese-CLIP 增强中文文字识别能力和表情包内涵识别能力,接近gpt4o、claude-3.5-sonnet的识别水平!☆22Updated 8 months ago
- 本项目使用LLaVA 1.6多模态模型实现以文搜图和以图搜图功能。☆20Updated last year
- Building a VLM model starts from the basic module.☆14Updated last year
- Build a simple basic multimodal large model from scratch. 从零搭建一个简单的基础多模态大模型🤖☆34Updated 9 months ago
- ☆46Updated last year
- Research Code for Multimodal-Cognition Team in Ant Group☆141Updated 9 months ago
- 商品图像检索、多模态、深度学习☆31Updated 3 years ago
- transformers结构的中文OFA模型☆129Updated 2 years ago
- This project is an image retrieval system based on DINOv2 and CLIP models, supporting both image-to-image and text-to-image retrieval. Us…☆13Updated last month
- a super easy clip model with mnist dataset for study☆106Updated last year
- Implementation of our paper, 'Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval.'☆23Updated last year
- demo natural language video db using CLIP☆25Updated 8 months ago
- ☆56Updated last year