Vincent Herrmann

transformerXL_PPO_JAX. Python

multiset-compression. Official code accompanying the arXiv paper Compressing Multisets with Large Alphabets

Score-Entropy-Discrete-Diffusion. [ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

dreamerv3-torch. Implementation of Dreamer v3 in pytorch.

dreamerv3. Mastering Diverse Domains through World Models

MidiTok. MIDI / symbolic music tokenizers for Deep Learning models 🎶

creative_ml. Creative Machine Learning course and notebook tutorials in JAX, PyTorch and Numpy

story-distiller. Python

LSUV-pytorch. Simple implementation of the LSUV initialization in PyTorch

multilinear-math. Swift library for tensor operations, machine learning and artificial intelligence

audiocraft. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

musiclm-pytorch. Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

open-musiclm. Implementation of MusicLM, a text to music model published by Google Research, with a few modifications.

gymnax. RL Environments in JAX 🌍

hyper-nn. Easy Hypernetworks in Pytorch and Jax

AudioMNIST. Python

minimal. Minimal is a Jekyll theme for GitHub Pages

COLD_decoding. Python

JSB-Chorales-dataset. Dataset for JSB Chorales at different temporal resolutions, with train, validation, test split from Boulanger-Lewandowski (2012).

spinningup. An educational resource to help anyone learn deep reinforcement learning.

ssqueezepy. Synchrosqueezing, wavelet transforms, and time-frequency analysis in Python

cluster_tool. Python

higher. higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

mirdata. Python library for working with Music Information Retrieval datasets

infinite-bach. Python

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

genmusic_demo_list. a list of demo websites for automatic music generation research

glumpy. Python+Numpy+OpenGL: fast, scalable and beautiful scientific visualization

mpl-scatter-density. :zap: Fast scatter density plots for Matplotlib :zap:

pizza-dough. This recipe is dedicated to helping you make the best possible pizza dough for Neapolitan pizza.

vispy-tutorial. tutorial about vispy

tsne-cuda. GPU Accelerated t-SNE for CUDA with Python bindings

WaveRNN. WaveRNN Vocoder + TTS

awesome-speech-recognition-speech-synthesis-papers. Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)

contrastive-predictive-coding. Keras implementation of Representation Learning with Contrastive Predictive Coding

prednet. Code and models accompanying "Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning"

VirtualKVM. Automatically toggles Bluetooth and Target Display Mode when you connect a Macbook to your iMac via Thunderbolt.

pyo. Python DSP module

Probabilistic-Programming-and-Bayesian-Methods-for-Hackers. aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

glow. Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

mathbox. Presentation-quality WebGL math graphing

VQ-VAE. VQ-VAE implementation / pytorch

spotify-dl. a script that allows you to download spotify songs or playlists , written in python

python-7digital-api. Acces to 7 digital API via simple python code

APSRR-2016. Audio Processing Seminar 2016: Reproducible Research

ListenMSD. A collection of Spotify playlists covering the Million Song Subset

MSongsDB. Code for the Million Song Dataset, the dataset contains metadata and audio analysis for a million tracks, a collaboration between The Echo Nest and LabROSA. See website for details.

ml-lib. A machine learning library for Max and Pure Data

kelletal2018. Parameters for the neural network used in Kell, Yamins, Shook, Norman-Haignere, and McDermott. "A task-optimized neural network replicates human auditory behavior, predicts brain responses, and reveals a cortical processing hierarchy." Neuron, 2018.

pycochleagram. Generate cochleagrams natively in Python. Ported from Josh McDermott's MATLAB code.

pd-externals-c. Source code for "Creating Pure Data Externals in C" tutorial series on YouTube

playground. PlayGround: AI Research into Multi-Agent Learning.

techtalks. Slides and Supplementary Material of the past TechTalks at the Karlsruhe Machine Learning, Statistics and AI Meetup

awesome-bioacoustic.

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

NAF. Experiments for the Neural Autoregressive Flows paper

griffin_lim. Implementation of the Griffin and Lim algorithm to recover an audio signal from a magnitude-only spectrogram.

tftb. A Python module for time-frequency analysis

colab_utils. assorted utils for use with `Colaboratory`

osx-gcc-installer. GCC Installer for OSX! Without Xcode!

jupyterlab. JupyterLab computational environment.

python3_with_pleasure. A short guide on features of Python 3 with examples

ENAS-pytorch. PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

RISE. RISE: "Live" Reveal.js Jupyter/IPython Slideshow Extension

SOM. Visualization of self-organizing map algorithm

Capsule-Network-Tutorial. Pytorch easy-to-follow Capsule Network tutorial

CycleGAN. Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

torch-stft. An STFT/iSTFT for PyTorch.

capsule-networks. A PyTorch implementation of the NIPS 2017 paper "Dynamic Routing Between Capsules".

Mocha.jl. Deep Learning framework for Julia

TensorFlow.jl. A Julia wrapper for TensorFlow

SampledSignals.jl. Core types for regularly-sampled multichannel signals like Audio, RADAR and Software-Defined Radio

bokeh. Interactive Data Visualization in the browser, from Python

holoviews. With Holoviews, your data visualizes itself.

yt. Main yt repository

tensorboardX. tensorboard for pytorch (and chainer, mxnet, numpy, ...)

NetworkxD3. D3 JavaScript networkx Graphs in Python

nninit. Weight initialization schemes for PyTorch nn.Modules

vision. Datasets, Transforms and Models specific to Computer Vision

Deep-learning-with-cats. Deep learning with cats (^._.^)

examples. A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

SNNs. Tutorials and implementations for "Self-normalizing networks"

functional-zoo. PyTorch and Tensorflow functional model definitions

sampleRNN_ICLR2017. SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

nitrain. Train AI models efficiently on medical images using any framework

tensorboard_logger. Log TensorBoard events without touching TensorFlow

tensorflow-on-google-computing-engine. A shell script to setup TensorFlow environment on Google Computing Engine.

Tensor-Flow-on-Google-Compute-Engine. A simple script to set up GCE environment in Google Cloud so it is ready to run TensorFlow - an Open Source Software Library for Machine Intelligence

improved_wgan_training. Code for reproducing experiments in "Improved Training of Wasserstein GANs"

d3. Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:

pyscatwave. Fast Scattering Transform with CuPy/PyTorch

visdom. A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy https://visdom.dev

pytorch-tutorial. PyTorch Tutorial for Deep Learning Researchers

fast-wavenet. Speedy Wavenet generation using dynamic programming :zap:

WassersteinGAN.tensorflow. Tensorflow implementation of Wasserstein GAN - arxiv: https://arxiv.org/abs/1701.07875

TensorFlow-VAE-GAN-DRAW. A collection of generative methods implemented with TensorFlow (Deep Convolutional Generative Adversarial Networks (DCGAN), Variational Autoencoder (VAE) and DRAW: A Recurrent Neural Network For Image Generation).

WassersteinGAN. Python

poole. The Jekyll Butler. A no frills responsive Jekyll blog theme.

pyVision. pyVision machine learning library

RxSwift. Reactive Programming in Swift

Swift-monad-Maybe-Reader-and-Try. Proof of concept: Maybe, Reader and Try monad

mac-dev-setup. A beginner's guide to setting up a development environment on macOS

node-panasync. Synchronises pictures from wifi enabled cameras, storing them on a NAS

iunxtio. Automatically exported from code.google.com/p/iunxtio

AIToolbox. A toolbox of AI modules written in Swift: Graphs/Trees, Support Vector Machines, Neural Networks, PCA, K-Means, Genetic Algorithms

Python-Arduino-Command-API. A Python library for communicating with Arduino microcontroller boards

python_lumix_control. Python module for controlling Panasonic wifi enabled cameras

BrainCore. The iOS and OS X neural network framework

swift-algorithm-club. Algorithms and data structures in Swift, with explanations!

stat212b. Topics Course on Deep Learning UC Berkeley