znsoftm

algorithm-note

该系列包括数组，链表，树，图，递归，DP，有序表等相关数据结构与算法的讲解及代码实现。

BaiPiaoOCR

chia-blockchain

Chia blockchain python implementation (full node, farmer, harvester, timelord, and wallet)

cogdl

CogDL: An Extensive Toolkit for Deep Learning on Graphs

Cool-NLPCV

Some Cool NLP and CV Repositories and Solutions （收集NLP中常见任务的开源解决方案、数据集、工具、学习资料等）

CZXing

C++ port of ZXing and ZBar for Android.

dtformats

Collection of data formats

JioNLP

中文 NLP 预处理工具包，准确、高效、易用 A Chinese NLP Preprocessing Library

KnowledgeDistillation

Knowledge distillation in text classification with pytorch. 知识蒸馏，中文文本分类，教师模型BERT、XLNET，学生模型biLSTM。

libcpuid

a small C library for x86 CPU detection and feature extraction

libffi-windows

License-Plate-Detector

基于Retinaface车牌检测,全新模型仅1.8MB.

ltp

Language Technology Platform

MarkTool

这是一款基于web、面向领域的通用文本标注工具，支持大规模实体标注、关系标注、事件标注、文本分类、基于字典匹配和正则匹配的自动标注以及用于实现归一化的标准名标注，同时也支持文本的迭代标注和实体的嵌套标注。标注规范可自定义且同类型任务中可“一次创建多次复用”。通过分级实体集合扩大了实体类型的规模，并设计了全新高效的标注方式，提升了用户体验和标注效率。此外，本工具增加了审核环节，可对多人的标注结果进行一致性检验、自动合并和手动调整，提高了标注结果的准确率。

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more

PyTorch-Raspberry-Pi-64-OS

PyTorch installation wheels for Raspberry Pi 64 OS

pytorchOCR

基于pytorch的ocr算法库，包括 psenet, pan, dbnet, sast , crnn

PytorchOCR-1

基于Pytorch的OCR工具库，支持常用的文字检测和识别算法

RapidOCR

rustdesk

An open source remote desktop client software

Text-Level-GNN

Text Level Graph Neural Network for Text Classification

threadpool11

A fast, lock-free, cross-platform C++11 thread pool library that is aiming to be lightweight and simple.

toutiao-text-classfication-dataset

今日头条中文新闻（文本）分类数据集

tvm-build

A library for building TVM programmatically.

tvm-test

a set of program and models to test TVM ( deep learning compiler)

vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Yolo-Fastest

:zap: Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+

YOLO-Nano

A new version YOLO-Nano

YOLOv5_NCNN

🍅 Deploy NCNN on mobile phones. Support Android and iOS. 移动端NCNN部署，支持Android与iOS。