ka1ipapa Goto Github PK

-pytorch-

【PyTorch】手把手教你跑通第一个神经网络

attention-is-all-you-need-pytorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

calculator

Windows Calculator: A simple yet powerful calculator that ships with Windows

capture_reid

可基于摄像头实时监控或录制的视频或静态图片进行行人检测(lffd)/跟踪(deep sort)和行人重识别(reid)。

ceng-407-408-2017-2018-project-face-and-iris-recognition

ceng-407-408-project-face-and-iris-recognition created by GitHub Classroom

cidr

Classroom Interaction Detection and Recognition System

classroom-attendance-using-face-recognition

System that can detect students entering the classroom and mark them present on a server. It uses a kinect camera as a video input source and first detects face from video frames. After detecting face, then the detected faces are compared against pre-loaded database to recognize each students and marks the detected and recognized students present in the mysql server.

ddt

Official repository of “DDT: Dual-branch Deformable Transformer for Image Denoising, ICME23”

face-recognition-based-attendance-system

Detect and recognize faces from database in a classroom

fast-reid

SOTA Re-identification Methods and Toolbox

hollow-software-for-picture-video-information-hiding-encryption-and-decryption

This is a software for Picture (Video) Information Hiding Encryption and Decryption.(Hollow 图片（视频）信息隐藏加解密软件)

image-denoising-using-deep-learning

infohiding_course

基于混沌系统的图像可逆信息隐藏算法

information-hiding-in-images

octave-face-recognition

Face recognition using Fourrier Transform in Octave and compatible with Matlab.

person_find

YOLOv3+行人重识别 实现特定行人检索。

person_search_demo

利用YOLOv3结合行人重识别模型，实现行人的检测识别，查找特定行人

personreid

行人重识别

pet-cgdnn

An Efficient Deep Learning Model for Automatic Modulation Recognition Based on Parameter Estimation and Transformation

pytorch-modulation-recognition

PyTorch Implementation Modulation Recognition Networks on the RadioML2016 Dataset

radio-modulation-recognition-networks

Radio modulation recognition with CNN, CLDNN, CGDNN and MCTransformer architectures. Best results were achieved with the CGDNN architecture, which has roughly 50,000 parameters, and the final model has a memory footprint of 636kB. More details can be found in my bachelor thesis linked in the readme file.

stm32-speech-recognition

基于STM32的孤立词语音识别

student_attendance_using_facial_recognition

A Combined Feature Extraction Method for Automated Face Recognition in Classroom Environment

transgroupnet

The Pytorch implement of the paper "Convolutional Neural Network Assisted Transformer for Automatic Modulation Recognition under Large CFOs and SROs"

watermarking_algorithm

参考文献：[1]谢荣生,赵欢喜,陈玉明.基于QR码的防伪电子票数字水印方法[J].厦门大学学报(自然科学版),2013,52(03):338-342.

yolov3

YOLOv3 in PyTorch > ONNX > CoreML > TFLite