hedj17

hedj17's Stars

• weiaicunzai/pytorch-cifar100

  Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)

  Language:Python4.3k1.2k

• snu-ccl/FHE-MP-CNN

  Implementation of deep ResNet model on CKKS scheme in Microsoft SEAL library using multiplexed parallel convolution

  Language:C++6712

• xxupiano/PAT-Advanced-Level

  PAT Advance Level

  Language:C++1

• xxupiano/LittleC-Compiler

  A compiler for Little-C

  Language:C++1

• xxupiano/MNIST_Digit_Recognition

  Language:Python1

• xxupiano/LightChatRoom

  A light chat room website

  Language:Java2

• xxupiano/PAT_Basic_Level

  PAT Basic Level

  Language:C++1

• xxupiano/DeepMelody

  Music Generation with LSTM

  Language:Python1

• xxupiano/ImprovingGeneratedPianoMIDI

  Ameliorate piano MIDI generated by machines

  Language:Python3

• xxupiano/ChineseMusicTransformer

  A REMI-based Transformer-XL for Chinese piano generation

  Language:Python5

• xxupiano/DeepKE

  An Open Toolkit for Knowledge Base Population（DeepKE是一个支持低资源、长篇章的开源知识抽取工具，具备命名实体识别、关系抽取和属性抽取等功能）

  2

• xxupiano/NLP-Loss-Pytorch

  Implementation of some unbalanced loss like focal_loss, dice_loss, DSC Loss, GHM Loss et.al

  1

• xxupiano/Class-balanced-loss-pytorch

  PyTorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples" reproduced by Irene.

  Language:Python1

• xxupiano/genmusic_demo_list

  a list of demo websites for automatic music generation research

  1

• lightbulb128/troy

  GPU implementation of BFV, CKKS and BGV homomorphic encryption schemes.

  Language:C++333

• KyoohyungHan/HELR

  Homomorphic Logistic Regression on Encrypted Data

  Language:C++4717

• OChicken/GPQHE

  A C library doing fully homomorphic encryption under the license of LGPL.

  Language:C82

• hedj17/DST

  This project implements two dynamic spatiotemporal interpolation (DST) methods, i.e., coarse-grained DST (CGDST) and fine-grained DST (FGDST) using both temporal and spatial interpolation results. Different from other hybrid spatiotemporal interpolation methods, they make differences in the contribution of temporal and spatial interpolation results and assign them with different weights. Both CGDST and FGDST treat each missing value differently and fill it by considering the reliability of both temporal and spatial interpolation results in terms of the lengths of its column gap and row gap. CGDST treats each missing value in a continuous missing area equally and all missing values have same lengths of column and row gaps and FGDST goes beyond CGDST and treats each missing value differently based on its temporal distance to the nearest real observed values in both forward and backward directions.

  Language:Python112

• gaoshiping/RuningTensor

  编译原理课程设计，专门用于矩阵运算的语言，现阶段已经完成词法分析和语法分析

  Language:C++41

• LinghaoChan/CSSummerCamp2022

  关于2022年CS保研夏令营通知公告的汇总。欢迎大家积极分享夏令营信息，资瓷一下互联网精神吼不吼啊？

  1.3k185

• notanevan/20-21-SEU-ASC

  20-21 ASC Student Supercomputer Challenge of the Southeast University Team

  Language:Python32