A Collection of Variational Autoencoders (VAE) in PyTorch.

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)

☁️ 🚀 📊 📈 Evaluating state of the art in AI

High-fidelity performance metrics for generative models in PyTorch

This is the repository of our article published in RecSys 2019 "Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches" and of several follow-up studies.

PyCIL: A Python Toolbox for Class-Incremental Learning

Code to accompany our paper Chen and Zimmermann (2020), "Open source cross-sectional asset pricing"

Experiments for understanding disentanglement in VAE latent representations

A research tool for the Iterated Prisoner's Dilemma

An elegant Python interface for visualization on the web platform to interactively generate insights into multidimensional images, point sets, and geometry.

PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.

🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox

Pweave is a scientific report generator and a literate programming tool for Python. It can capture the results and plots from data analysis and works well with numpy, scipy and matplotlib.

Effortless method to record provenance in Python

Lightweight fast function pipeline (DAG) creation in pure Python for scientific workflows 🕸️🧪

Live code in Pandoc Markdown

A curated list of reproducible research case studies, projects, tutorials, and media

Generate custom Docker and Singularity images, and minimize existing containers