Shoubin Li's repositories
darknet_face_with_landmark
加入关键点的darknet训练框架，轻量级的人脸检测，支持ncnn推理
Android-PaddleOCR
PaddleOCR Android Version。From https://github.com/PaddlePaddle/PaddleOCR
Android_NCNN_yolov4-tiny
yolov4-tiny ncnn android sample
BERT-BiLSTM-CRF-NER
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
chrome-plugin-demo
《Chrome插件开发全攻略》配套完整Demo，欢迎clone体验
DuiLib_Ultimate
duilib 旗舰版-高分屏、多语言、样式表、资源管理器、异形窗口、窗口阴影、简单动画
EasySpider
A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。
fmj
FMJ (FFMpeg for Java)。通过Java调用FFMpeg命令的方式来对音视频进行处理（获取信息、截图等等）。
KG_RAG
Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks
License-Plate-Detector
基于Retinaface车牌检测,全新模型仅1.8MB.
lishoubin.github.io
Lishoubin CV
ncnn_example
ncnn example: mask detection: anticonv face detection: retinaface&&mtcnn&¢erface, track: iou tracking, landmark: zqcnn, recognize: mobilefacenet classifier: mobilenet object detecter: mobilenetssd
ncnn_paddleocr
Android paddleocr demo infer by ncnn
NER_DEMO
中文命名实体识别NER。用keras实现BILSTM+CRF、IDCNN+CRF、BERT+BILSTM+CRF进行实体识别。结果当然是BERT+BILSTM+CRF最好啦。
PaddleWebOCR
开源的中英文离线 OCR，使用 PaddleOCR 实现，提供了简单的 Web 页面及接口
PyMuPDF-Utilities
Demos, examples and utilities using PyMuPDF
SeetaFace2
SeetaFace 2
spring-cloud-tencent
Spring Cloud Tencent is a Spring Cloud based Service Governance Framework provided by Tencent.
TengineKit
TengineKit - Free, Fast, Easy, Real-Time Face Detection & Face Landmarks & Face Attributes & Hand Detection & Hand Landmarks & Body Detection & Body Landmarks & Iris Landmarks & Yolov5 SDK On Mobile.
tensorflow-windows-wheel
Tensorflow prebuilt binary for Windows
Towards-Realtime-MOT
Joint Detection and Embedding for fast multi-object tracking
x-spreadsheet
A web-based JavaScript（canvas） spreadsheet
Yet-Another-EfficientDet-Pytorch
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.