Pytorch implementation of the popular Improv RNN model originally proposed by the Magenta team.

Overview

Pytorch Implementation of Improv RNN

Overview

This code is a pytorch implementation of the popular Improv RNN model originally implemented by the Magenta team. The model is able to generate melodies conditioned on a given chord progression.
The specific model implemented in this repository is the Chord Pitches Improv model which encodes chords as the concatenation of the following length-12 vectors:

  • a one-hot encoding of the chord root pitch class, e.g. [0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0] for a D major (or minor, etc.) chord
  • a binary vector indicating presence or absence of each pitch class, e.g. [1, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0] for a C7#9 chord
  • a one-hot encoding of the chord bass pitch class, which is usually the same as the chord root pitch class except in the case of "slash chords" like C/E

You can either use a pre-trained checkpoint of the model or train your own using the steps below.

Installation

Install Required Libraries

pip install -r requirements.txt

Generate a Melody Given Backing Chords

A pretrained checkpoint of the model can be found in the "checkpoints" folder. The checkpoint has been trained for 1000 epochs on the OpenEWLD dataset.

python 003_generate_melody.py --backing_chords "C G Am F C G F C" --output out.mid

This will generate a melody starting with a middle C over the chord progression C G Am F C G F C, where each chord lasts one bar. You can modify the backing chords as you like using the backing_chords parameter. You can define where the generated midi file should be saved with the output parameter.

An example of the generated RNN features is visualized here:

Example Generated Note Events

Train Your Own Model

Download OpenEWLD Dataset

To train the model, the OpenEWLD dataset is used. OpenEWLD is a subset of the Wikifonia Leadsheet Dataset reduced to only copyright free songs. A lead sheet is a musical score that contains a notation of the melody and the underlying chord progression of a song.
The song examples are in the compressed musicxml (*.MXL) format which can be parsed in to sequences of note events using the note-seq library.

Dataset Preparation

Extract features from musicxml files and store them in a h5 file.

python 001_create_dataset.py --input C:/Datasets/OpenEWLD/dataset

Training

Track metrics using Tensorboard

python 002_train.py --num_epochs 1000

Track metrics using Tensorboard

tensorboard --logdir ./logs/

The curves of the loss and accuracy over the training epochs are shown in tensorboard:

Tensorboard

Owner
Sebastian Murgul
CEO and Research Scientist at Klangio. Working on Automatic Music Transcription.
Sebastian Murgul
Official Pytorch implementation of 'RoI Tanh-polar Transformer Network for Face Parsing in the Wild.'

Official Pytorch implementation of 'RoI Tanh-polar Transformer Network for Face Parsing in the Wild.'

Jie Shen 125 Jan 08, 2023
[ICLR'21] Counterfactual Generative Networks

This repository contains the code for the ICLR 2021 paper "Counterfactual Generative Networks" by Axel Sauer and Andreas Geiger. If you want to take the CGN for a spin and generate counterfactual ima

88 Jan 02, 2023
Neural Scene Graphs for Dynamic Scene (CVPR 2021)

Implementation of Neural Scene Graphs, that optimizes multiple radiance fields to represent different objects and a static scene background. Learned representations can be rendered with novel object

151 Dec 26, 2022
Junction Tree Variational Autoencoder for Molecular Graph Generation (ICML 2018)

Junction Tree Variational Autoencoder for Molecular Graph Generation Official implementation of our Junction Tree Variational Autoencoder https://arxi

Wengong Jin 418 Jan 07, 2023
Paddle implementation for "Highly Efficient Knowledge Graph Embedding Learning with Closed-Form Orthogonal Procrustes Analysis" (NAACL 2021)

ProcrustEs-KGE Paddle implementation for Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis 🙈 A more detailed re

Lincedo Lab 4 Jun 09, 2021
Conservative Q Learning for Offline Reinforcement Reinforcement Learning in JAX

CQL-JAX This repository implements Conservative Q Learning for Offline Reinforcement Reinforcement Learning in JAX (FLAX). Implementation is built on

Karush Suri 8 Nov 07, 2022
PyTorch-centric library for evaluating and enhancing the robustness of AI technologies

Responsible AI Toolbox A library that provides high-quality, PyTorch-centric tools for evaluating and enhancing both the robustness and the explainabi

24 Dec 22, 2022
Wordplay, an artificial Intelligence based crossword puzzle solver.

Wordplay, AI based crossword puzzle solver A crossword is a word puzzle that usually takes the form of a square or a rectangular grid of white- and bl

Vaibhaw 4 Nov 16, 2022
A PyTorch implementation of "Predict then Propagate: Graph Neural Networks meet Personalized PageRank" (ICLR 2019).

APPNP ⠀ A PyTorch implementation of Predict then Propagate: Graph Neural Networks meet Personalized PageRank (ICLR 2019). Abstract Neural message pass

Benedek Rozemberczki 329 Dec 30, 2022
This is a re-implementation of TransGAN: Two Pure Transformers Can Make One Strong GAN (CVPR 2021) in PyTorch.

TransGAN: Two Transformers Can Make One Strong GAN [YouTube Video] Paper Authors: Yifan Jiang, Shiyu Chang, Zhangyang Wang CVPR 2021 This is re-implem

Ahmet Sarigun 79 Jan 05, 2023
Dynamic Capacity Networks using Tensorflow

Dynamic Capacity Networks using Tensorflow Dynamic Capacity Networks (DCN; http://arxiv.org/abs/1511.07838) implementation using Tensorflow. DCN reduc

Taeksoo Kim 8 Feb 23, 2021
Ankou: Guiding Grey-box Fuzzing towards Combinatorial Difference

Ankou Ankou is a source-based grey-box fuzzer. It intends to use a more rich fitness function by going beyond simple branch coverage and considering t

SoftSec Lab 54 Dec 24, 2022
Progressive Growing of GANs for Improved Quality, Stability, and Variation

Progressive Growing of GANs for Improved Quality, Stability, and Variation — Official TensorFlow implementation of the ICLR 2018 paper Tero Karras (NV

Tero Karras 5.9k Jan 05, 2023
Camera ready code repo for the NeuRIPS 2021 paper: "Impression learning: Online representation learning with synaptic plasticity".

Impression-Learning-Camera-Ready Camera ready code repo for the NeuRIPS 2021 paper: "Impression learning: Online representation learning with synaptic

2 Feb 09, 2022
Multi-Object Tracking in Satellite Videos with Graph-Based Multi-Task Modeling

TGraM Multi-Object Tracking in Satellite Videos with Graph-Based Multi-Task Modeling, Qibin He, Xian Sun, Zhiyuan Yan, Beibei Li, Kun Fu Abstract Rece

Qibin He 6 Nov 25, 2022
Cycle Consistent Adversarial Domain Adaptation (CyCADA)

Cycle Consistent Adversarial Domain Adaptation (CyCADA) A pytorch implementation of CyCADA. If you use this code in your research please consider citi

Hyunwoo Ko 2 Jan 10, 2022
PyTorch implementation of "LayoutTransformer: Layout Generation and Completion with Self-attention"

PyTorch implementation of "LayoutTransformer: Layout Generation and Completion with Self-attention" to appear in ICCV 2021

Kamal Gupta 75 Dec 23, 2022
Code for approximate graph reduction techniques for cardinality-based DSFM, from paper

SparseCard Code for approximate graph reduction techniques for cardinality-based DSFM, from paper "Approximate Decomposable Submodular Function Minimi

Nate Veldt 1 Nov 25, 2022
Code for our paper "Graph Pre-training for AMR Parsing and Generation" in ACL2022

AMRBART An implementation for ACL2022 paper "Graph Pre-training for AMR Parsing and Generation". You may find our paper here (Arxiv). Requirements pyt

xfbai 60 Jan 03, 2023
PyTorch implementation of ICLR 2022 paper PiCO: Contrastive Label Disambiguation for Partial Label Learning

PiCO: Contrastive Label Disambiguation for Partial Label Learning This is a PyTorch implementation of ICLR 2022 paper PiCO: Contrastive Label Disambig

çŽ‹çš“æłą 147 Jan 07, 2023