spkgyk Goto Github PK

aiops

This is our repo for the final project of the Advanced Network Management course at Tsinghua University

anki-cc-cedict

Add some new features.

anki-pinyin

audio-only-speech-separation

binary-strings

How many ways to compose binary strings (made up of 0s and 1s) of length 𝑛 that do not contain “010” or “101”?

c-and-a-hwk

Code for Tsinghua Combinatorics and Algorithms design homeworks (OJ)

class-conditioned-vae

Deep Generative Models: Class-conditioned Variational Autoencoder (VAE) for generating MNIST digits.

cogdl

CogDL: An Extensive Research Toolkit for Graphs

emorobertanet

Emotion classification from text, using roberta-base as a base model on the HuggingFace 'emotion' dataset.

functional-programming

irls-logistic-regression

Machine Learning. Lagrange multipliers, support vector machines (SVM) and iteratively reweighted least squares (IRLS) for Logistic Regression.

karen

KAREN: Unifying Hatespeech Detection and Benchmarking

rtfs-net

Official code release for "RTFS-Net: Recurrent time-frequency modelling for efficient audio-visual speech separation", accepted ICLR 2024

satellite-classification-dl

Solution to Statoil/C-CORE Iceberg Classifier Challenge using ensemble learning based on ResNeXt-29 & VGG16.

speech-denoising

Speech Denoising project for the Deep Learning course at Tsinghua University, spring 2021

tdfnet

Official code release for "TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion", accepted ICIST 2023