All Projects → L0SG → seqgan-music

L0SG / seqgan-music

Licence: other
Implementation of a paper "Polyphonic Music Generation with Sequence Generative Adversarial Networks" in TensorFlow

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to seqgan-music

Music-generation-cRNN-GAN
cRNN-GAN to generate music by training on instrumental music (midi)
Stars: ✭ 38 (+80.95%)
Mutual labels:  generative-adversarial-network, music-generation
bmusegan
Code for “Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation”
Stars: ✭ 58 (+176.19%)
Mutual labels:  generative-adversarial-network, music-generation
Semantic Pyramid for Image Generation
PyTorch reimplementation of the paper: "Semantic Pyramid for Image Generation" [CVPR 2020].
Stars: ✭ 45 (+114.29%)
Mutual labels:  generative-adversarial-network
GAN-Project-2018
GAN in Tensorflow to be run via Linux command line
Stars: ✭ 21 (+0%)
Mutual labels:  generative-adversarial-network
catgan pytorch
Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
Stars: ✭ 50 (+138.1%)
Mutual labels:  generative-adversarial-network
esrgan
Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution
Stars: ✭ 48 (+128.57%)
Mutual labels:  generative-adversarial-network
generating-music
🎷 Artificial Composition of Multi-Instrumental Polyphonic Music
Stars: ✭ 28 (+33.33%)
Mutual labels:  music-generation
CS231n
PyTorch/Tensorflow solutions for Stanford's CS231n: "CNNs for Visual Recognition"
Stars: ✭ 47 (+123.81%)
Mutual labels:  generative-adversarial-network
AdvSegLoss
Official Pytorch implementation of Adversarial Segmentation Loss for Sketch Colorization [ICIP 2021]
Stars: ✭ 24 (+14.29%)
Mutual labels:  generative-adversarial-network
Awesome-Text-to-Image
A Survey on Text-to-Image Generation/Synthesis.
Stars: ✭ 251 (+1095.24%)
Mutual labels:  generative-adversarial-network
AdverseBiNet
Improving Document Binarization via Adversarial Noise-Texture Augmentation
Stars: ✭ 34 (+61.9%)
Mutual labels:  generative-adversarial-network
gan tensorflow
Automatic feature engineering using Generative Adversarial Networks using TensorFlow.
Stars: ✭ 48 (+128.57%)
Mutual labels:  generative-adversarial-network
vaegan
An implementation of VAEGAN (variational autoencoder + generative adversarial network).
Stars: ✭ 88 (+319.05%)
Mutual labels:  generative-adversarial-network
Adventures-with-GANS
Showcasing various fun adventures with GANs
Stars: ✭ 13 (-38.1%)
Mutual labels:  generative-adversarial-network
pytorch-arda
A PyTorch implementation for Adversarial Representation Learning for Domain Adaptation
Stars: ✭ 49 (+133.33%)
Mutual labels:  generative-adversarial-network
StyleGANCpp
Unofficial implementation of StyleGAN's generator
Stars: ✭ 25 (+19.05%)
Mutual labels:  generative-adversarial-network
tgan
The implementation of Temporal Generative Adversarial Nets with Singular Value Clipping
Stars: ✭ 70 (+233.33%)
Mutual labels:  generative-adversarial-network
genmusic
Generative Music- a stochastic modal music generator
Stars: ✭ 17 (-19.05%)
Mutual labels:  music-generation
SeqGAN-PyTorch
Implementation of Sequence Generative Adversarial Nets with Policy Gradient in PyTorch
Stars: ✭ 40 (+90.48%)
Mutual labels:  seqgan
GAN-auto-write
Generative Adversarial Network that learns to generate handwritten digits. (Learning Purposes)
Stars: ✭ 18 (-14.29%)
Mutual labels:  generative-adversarial-network

This repo is a work-in-progress status without code cleanup and refactoring.

Introduction

This is an implementation of a paper Polyphonic Music Generation with Sequence Generative Adversarial Networks in TensorFlow.

Hard-forked from the official SeqGAN code.

Requirements

Python 2.7

Tensorflow 1.4 or newer (tested on 1.9)

pip packages: music21 4.1.0, pyyaml, nltk, pathos

How to use

python music_seqgan.py for full training run.

SeqGAN.yaml contains (almost) all hyperparameters that you can play with.

5 sample MIDI sequences are automatically generated per epoch.

Dataset

The model uses a MIDI version of Nottingham database (http://abc.sourceforge.net/NMD/) as the dataset.

Preprocessed musical word tokens are included in the "dataset" folder.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].