Training, generation, and analysis code for Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics

Last update: Oct 22, 2022

Overview

Location-Aware Generative Adversarial Networks (LAGAN) for Physics Synthesis

This repository contains all the code used in L. de Oliveira (@lukedeo), M. Paganini (@mickypaganini), B. Nachman (@bnachman), Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis [arXiv:1701.05927]

Citations

You are more than welcome to use the open data and open-source software provided here for any of your projects, but we kindly ask you that you please cite them using the DOIs provided below:

Asset	Location
Source Code (this repository)
Data (Pythia images)
Model Weights
Docker image (generation)

If you're using ideas or methods discussed in the paper, with or without using the software, please cite:

@article{lagan,
      author         = "de Oliveira, Luke and Paganini, Michela and Nachman, Benjamin",
      title          = "{Learning Particle Physics by Example: Location-Aware
                        Generative Adversarial Networks for Physics Synthesis}",
      year           = "2017",
      eprint         = "1701.05927",
      archivePrefix  = "arXiv",
      primaryClass   = "stat.ML",
      SLACcitation   = "%%CITATION = ARXIV:1701.05927;%%"
}

Getting Started

To clone everything necessary, you'll need to run git clone --recursive https://github.com/lukedeo/adversarial-jets to fetch all the submodules (you can add a -j6 or some other number to launch concurrent clones).

This repository is structured as such:

generation
models
analysis

Generation

[TODO: allow for preprocessing in Docker] This folder links to the submodule used for generating Pythia images.

Models

This folder contains the Keras models used for training the LAGAN seen in the paper. By running python train.py -h from this folder, you should see all available options for running the training, as well as how to find / download the data required.

Analysis

[TODO: update filenames, download links, etc.] This folder contains a jupyter nootbook that will guide you through the production of the plots that appear in the paper. You will be able to reproduce them and modify them as you wish using our trained models and open datasets, or reuse the plotting functions to visualize the performance of your own LAGAN.

Simply run: jupyter notebook plots.ipynb

Code for the paper "TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks"

TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks This is a Python3 / Pytorch implementation of TadGAN paper. The associated

92 Dec 3, 2022

This code uses generative adversarial networks to generate diverse task allocation plans for Multi-agent teams.

Mutli-agent task allocation This code uses generative adversarial networks to generate diverse task allocation plans for Multi-agent teams. To change

5 Oct 12, 2022

PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"

DiscoGAN in PyTorch PyTorch implementation of Learning to Discover Cross-Domain Relations with Generative Adversarial Networks. * All samples in READM

1k Jan 4, 2023

Official implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"

DiscoGAN Official PyTorch implementation of Learning to Discover Cross-Domain Relations with Generative Adversarial Networks. Prerequisites Python 2.7

754 Dec 29, 2022

Semi-supervised Representation Learning for Remote Sensing Image Classification Based on Generative Adversarial Networks

SSRL-for-image-classification Semi-supervised Representation Learning for Remote Sensing Image Classification Based on Generative Adversarial Networks

2 Nov 19, 2021

Based on the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral

Geometry-aware Instance-reweighted Adversarial Training This repository provides codes for Geometry-aware Instance-reweighted Adversarial Training (ht

47 Dec 22, 2022

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis Jungil Kong, Jaehyeon Kim, Jaekyoung Bae In our paper, we p

31 Dec 8, 2022

Minimal PyTorch implementation of Generative Latent Optimization from the paper "Optimizing the Latent Space of Generative Networks"

Minimal PyTorch implementation of Generative Latent Optimization This is a reimplementation of the paper Piotr Bojanowski, Armand Joulin, David Lopez-

117 Nov 27, 2022

[ICLR 2021, Spotlight] Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks, ICLR 2021 (Spotlight) Demo | Paper [NEW!] Time to play with our interac

373 Jan 2, 2023

Comments

Add other architectures to models/

In the arXiv paper, we say that we tried different things along the way (FCN, CNN, 2-stream, etc.) and that although we don't report the results for all, the architectures are available on github. We should add them to the models/ folder.

opened by mickypaganini 1
Link github with Zenodo for code citation

This is something I think only @lukedeo can do, given that the repo is under his name. Here are the instructions: https://guides.github.com/activities/citable-code/

opened by mickypaganini 1
To-do
[x] We need to not train on the whole 2M sample (too long to experiment). Note that these samples are unshuffled and we need to shuffle them as there is a big block of signal and a big block of bkg.

[x] We should convert all instances of U[-1, 1] noise to N(0, 1) noise

[x] We should make some plotting code to evaluate after training. Maybe start with trying to make some plots for the average jets that look like the ones in the paper. There is some code for plotting average / individual jets here.
opened by lukedeo 0

Releases(0.1.0)

0.1.0(Mar 19, 2017)

Initial release of fully reproducible repository, with model weights available.
Source code(tar.gz)
Source code(zip)

Training, generation, and analysis code for Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics

Related tags

Overview

Location-Aware Generative Adversarial Networks (LAGAN) for Physics Synthesis

Citations

Getting Started

Generation

Models

Analysis

You might also like...

Code for the paper "TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks"

This code uses generative adversarial networks to generate diverse task allocation plans for Multi-agent teams.

PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"

Official implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"

Semi-supervised Representation Learning for Remote Sensing Image Classification Based on Generative Adversarial Networks

Based on the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Minimal PyTorch implementation of Generative Latent Optimization from the paper "Optimizing the Latent Space of Generative Networks"

[ICLR 2021, Spotlight] Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

Comments

Add other architectures to models/

Link github with Zenodo for code citation

To-do

Releases(0.1.0)

0.1.0(Mar 19, 2017)

Owner

Deep Learning for HEP

Code for 1st place solution in Sleep AI Challenge SNU Hospital

Pytorch for Segmentation

Mouse Brain in the Model Zoo

Implementation of the Point Transformer layer, in Pytorch

Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation

MakeItTalk: Speaker-Aware Talking-Head Animation

Coded illumination for improved lensless imaging

🎯 A comprehensive gradient-free optimization framework written in Python

This repository provides an efficient PyTorch-based library for training deep models.

Job-Recommend-Competition - Vectorwise Interpretable Attentions for Multimodal Tabular Data

MDMM - Learning multi-domain multi-modality I2I translation

Build Low Code Automated Tensorflow, What-IF explainable models in just 3 lines of code.

[ICLR 2021] Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments.

Fully Convlutional Neural Networks for state-of-the-art time series classification

Pytorch Implementation of Residual Vision Transformers(ResViT)

On the Limits of Pseudo Ground Truth in Visual Camera Re-Localization

Code for "Universal inference meets random projections: a scalable test for log-concavity"

ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)

MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving

PyTorch implementation of EfficientNetV2