Implementation of the Wave-U-Net for audio source separation

Implement Wave-U-Net by PyTorch, and migrate it to the speech enhancement.

A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.

Python Heart Rate Analysis Package, for both PPG and ECG signals

Code for the paper "Efficient Dataset Distillation using Random Feature Approximation"

Code for the paper Hybrid Spectrogram and Waveform Source Separation

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

Scalable and user friendly neural 🧠 forecasting algorithms.

Foundation Models for Time Series

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

A fully invertible U-Net for memory efficiency in Pytorch.

A universal time series representation learning framework

Using CNN with autoencoder features for smartphone-based Human Activity Recognition in real use case scenarios. (Final project for Human Data Analytics class at UNIPD).

Python implementation of the Learning Time-Series Shapelets method, that learns a shapelet-based time-series classifier with gradient descent.

The Implementation of FastSpeech based on pytorch.

Awesome Deep Learning for Time-Series Imputation, including an unmissable paper and tool list about applying neural networks to impute incomplete time series containing NaN missing values/data

Multivariate Time Series Transformer, public version

Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight)

Official implementation of our ICLR 2023 paper "Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting"

Official PyTorch implementation of BigVGAN (ICLR 2023)

Repository of Transformer based PyTorch Time Series Models

(Realtime) Temporal Convolutions in PyTorch

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

STUMPY is a powerful and scalable Python library for modern time series analysis

RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks

shapelets is a python package that implements several shapelet functions and some of their significant applications in science and astronomy.