Pinned Repositories
modelscope
ModelScope: bring the notion of Model-as-a-Service to life.
ccmusic_eval
Evaluation for all classification tasks among CCMUSIC
monet-joe
花式自定义Github首页
Piano-Classification
This study converts piano recordings to mel spectrogram and classifies them by SOTA pre-trained neural network backbones in CV. Comparative experiments show that SqueezeNet achieves a best classification accuracy of 92.37%.|该项目将钢琴录音转为为mel频谱图，使用微调后的前沿计算机视觉领域预训练深度学习骨干网络对其进行分类，对比实验可知SqueezeNet作为最优网络正确率可达92.37%
vits
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
eLuvLetter
https://gitee.com/MuGeminorum/eLuvLetter
FluidS
It uses Navier-Stokes equation as the physical model, the numerical solution obtained by real-time calculation includes scalar and velocity fields displayed in the OpenGL control. Users have a choice of 64x64 and 128x128 resolutions and 7 color options.|使用纳维-斯托克斯方程作为物理模型，实时计算得到的数值解便是标量场及速度场的分布情况，并显示在OpenGL控件中。用户有64x64和128x128两种分辨率以及7种颜色选项可供选择。
Mathematica-Music-Pack
This macro package simplifies the arrangement input structure in the Mathematica platform sound module, reducing the amount of code keyed in by the composer and removing a lot of repetitive code structure and functional flaws in the original synthesis on special sounds.|此宏包可简化Mathematica平台声音模块中的编曲输入结构，降低作曲者键入代码量，去除原有合成中大量重复的代码结构和特殊音效上的功能缺陷。
Medical_Image_Computing
Medical image computing (MIC) is an interdisciplinary field, there are three essential medical image analysis techniques: medical image enhancement (MIE) and medical image segmentation (MIS).|医学图像计算 (MIC) 是计算机科学、信息工程、电气工程、物理学、数学和医学交叉的交叉学科领域。在 MIC 领域内，存在三种基本的医学图像分析技术：医学图像增强 (MIE) 和医学图像分割（MIS）。
WiFi-Sharer
Sharer developed in VB.NET framework can turn a Windows notebook equipped with a shareable wireless network card into a WiFi transmitter; It includes a network speed monitor, which can calculate the upload and download rates in real time.|Sharer在VB.NET框架下设计的界面，是一款可将装有可共享无线网卡的Windows笔记本变身成WiFi发射器的软件；含有一个网速监控器，可实时计算上传及下载速率。
monet-joe's Repositories
monet-joe/Piano-Classification
This study converts piano recordings to mel spectrogram and classifies them by SOTA pre-trained neural network backbones in CV. Comparative experiments show that SqueezeNet achieves a best classification accuracy of 92.37%.|该项目将钢琴录音转为为mel频谱图，使用微调后的前沿计算机视觉领域预训练深度学习骨干网络对其进行分类，对比实验可知SqueezeNet作为最优网络正确率可达92.37%
monet-joe/ccmusic_eval
Evaluation for all classification tasks among CCMUSIC
monet-joe/monet-joe
花式自定义Github首页
monet-joe/vits
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech