A dataset of foreign object debris (FOD) designed for computer vision applications.

This implements training of popular model architectures, such as AlexNet, ResNet and VGG on the ImageNet dataset(Now we supported alexnet, vgg, resnet, squeezenet, densenet)

Python code to read text from a PDF file (OCR).

CDLA: A Chinese document layout analysis (CDLA) dataset

基于电商数据微调的Qwen2.5系列的电商大模型，电商数据sft后电商大模型。是https://github.com/leeguandong/EcommerceLLM的升级版本。qwen2.5的效果很好。

based on yolo-high-level project (detect\pose\classify\segment\):include yolov5\yolov7\yolov8\ core ,improvement research ,SwintransformV2 and Attention Series. training skills, business customizat…

复现大模型相关算法及一些学习记录

YOLOv8 PySide页面 💖

License plate recognition system based on YOLOv8 + OCR technology and build webUI with Gradio

基于LangChain和ChatGLM-6B等系列LLM的针对本地知识库的自动问答

这是一个用于与 RAGflow API 交互的 Python 客户端，支持数据集管理、文件管理、分块管理、聊天助手管理以及代理管理的完整功能。

基于RAG的私有知识库问答系统

Different attention modules integrated in the layer 10 of YOLOv8 algorithm.

Ultralytics YOLO 🚀

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

The dataset I am using is NEU-DET, which uses yolov8 and its improved models (including Coordinate Attention and Swin Transformer) for defect detection

基于vllm部署qwen2.5_vl实现视频流的实时识别

Analysis of Chinese and English layouts 中英文版面分析

PDF解析（文字，章节，表格，图片，参考），基于大模型(ChatGLM2-6B, RWKV)+langchain+streamlit的PDF问答，摘要，信息抽取

基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。

基于Pytorch实现的语音情感识别

LangChain 的中文入门教程

中文langchain项目|小必应，Q.Talk，强聊，QiangTalk

Production-ready platform for agentic workflow development.

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

通义千问VLLM推理部署DEMO

Fine-tuning of Flan-5T LLM for text classification 🤖 focuses on adapting a state-of-the-art language model to enhance its ability to classify text data.

今日头条中文新闻（文本）分类数据集

The simplest, fastest repository for training/finetuning medium-sized GPTs.