runrunrun1994

ncnn-android-deeplabv3plus

The deeplabv3+ person segmentation android example.

Person_Segmentation

The inference implementation of the deeplabV3+ person segementation algorithm.

yolov5-ppl.nn

Implement yolov5 using ppl.nn

CenterFace

face detection

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M

CRNN_Chinese_Characters_Rec

(CRNN) Chinese Characters Recognition.

DeepVision

在我很多项目中用到的CV算法推理框架应用。

FFMpegStudy

FFMpeg的实践工程

HelloGit

Image

image2csv

Convert tables stored as images to an usable .csv file

ImageProcess

libfacedetection

An open source library for face detection in images. The face detection speed can reach 1000FPS.

libfacedetection.train

The training program for libfacedetection for face detection and 5-landmark detection.

model-compression

model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for binary value of feature(A))

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

ncnn-android-yolov5

The YOLOv5 object detection android example

pytorch-cpp

C++ Implementation of PyTorch Tutorial for Deep Learning Researchers

pytorch_face_landmark

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Up to 100FPS landmark inference on CPU.

stylegan2-pytorch

Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

tensorRTIntegrate

TensorRT ONNX Plugin、Inference、Compile

weiboSpider

新浪微博爬虫，用python爬取新浪微博数据

yaskawa-servo-sigma7

Servo source code

yolo-tensorrt

darknet -> tensorrt. TensorRT yoloV123 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.

YOLObile

This is the implementation of YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design

YoloV3-TensorRT

Run YoloV3 with the newest TensorRT6.0 at 37 fps on NVIIDIA 1060.

yolov5-rt-stack

yolort / yet another yolov5, with its runtime stack for libtorch, onnx, tvm, ncnn and specialized accelerators.

baidu-qa-100w

:table: 百度QA100万数据集

search2ai

让你的大模型自动联网

WeChatMsg

提取微信聊天记录，将其导出成HTML、Word、CSV文档永久保存，对聊天记录进行分析生成年度聊天报告