Pytorch implementation of Rosca, Mihaela, et al. "Variational Approaches for Auto-Encoding Generative Adversarial Networks."

Overview

alpha-GAN

Unofficial pytorch implementation of Rosca, Mihaela, et al. "Variational Approaches for Auto-Encoding Generative Adversarial Networks." arXiv preprint arXiv:1706.04987 (2017).

I've got visually reasonable results on CIFAR-10 (see notebook). As the authors state, alpha-GAN is sensitive to changes in the network architectures. It seems important to keep batch normalization out of the code discriminator (C).

Deviations From The Paper

In the original paper (v1 on arXiv), prior and posterior terms are swapped in the code discriminator loss (equations 16 and 17 in Algorithm 1). Authors have confirmed.

Algorithm 1 in the paper is vague as to how each network should be updated; it doesn't account for SGD. The authors have confirmed that each of the four networks is updated separately in their experiments. However, in this implementation, encoder and generator (E and G networks) are updated jointly and share an optimizer. It may be worth revisiting the sequence and separation of optimizers.

This implementation adds the latent space cycle loss alluded to in the paper via an optional hyperparameter z_lambd. When z_lambd is nonzero, generated and reconstructed x will be run through the encoder and compared to the original sampled and encoded z.

Basic Usage

from alphagan import AlphaGAN

E, G, D, C = ... #torch.nn.Module

model = AlphaGAN(E, G, D, C, lambd=10, latent_dim=128)
if use_gpu:
  model = model.cuda()

X_train, X_valid = ... #torch.utils.data.DataSet

train_loader, valid_loader = ... #torch.utils.data.DataLoader

model.fit(train_loader, valid_loader, n_iter=(2,1,1), n_epochs=4, log_fn=print)

# encode and reconstruct
z_valid, x_recon = model(X_valid[:batch_size])

# sample from the generative model
z, x_gen = model(batch_size, mode='sample')

Supply any torch.nn.Module encoder, generator, discriminator, and code discriminator at construction and any torch.optim.Optimizer constructors and torch.utils.DataLoader to fit().

Examples

alphagan/examples/CIFAR.ipynb

Progress Bars

Install tqdm for progress bars. To get working nested progress bars in jupyter notebooks: pip install -e git+https://github.com/dvm-shlee/[email protected]#egg=tqdm

Owner
Victor Shepardson
Victor Shepardson
Everything you want about DP-Based Federated Learning, including Papers and Code. (Mechanism: Laplace or Gaussian, Dataset: femnist, shakespeare, mnist, cifar-10 and fashion-mnist. )

Differential Privacy (DP) Based Federated Learning (FL) Everything about DP-based FL you need is here. (所有你需要的DP-based FL的信息都在这里) Code Tip: the code o

wenzhu 83 Dec 24, 2022
PyTorch code for Composing Partial Differential Equations with Physics-Aware Neural Networks

FInite volume Neural Network (FINN) This repository contains the PyTorch code for models, training, and testing, and Python code for data generation t

Cognitive Modeling 20 Dec 18, 2022
A Python implementation of active inference for Markov Decision Processes

A Python package for simulating Active Inference agents in Markov Decision Process environments. Please see our companion preprint on arxiv for an ove

235 Dec 21, 2022
Semantic Image Synthesis with SPADE

Semantic Image Synthesis with SPADE New implementation available at imaginaire repository We have a reimplementation of the SPADE method that is more

NVIDIA Research Projects 7.3k Jan 07, 2023
An open source machine learning library for performing regression tasks using RVM technique.

Introduction neonrvm is an open source machine learning library for performing regression tasks using RVM technique. It is written in C programming la

Siavash Eliasi 33 May 31, 2022
The codes and related files to reproduce the results for Image Similarity Challenge Track 2.

ISC-Track2-Submission The codes and related files to reproduce the results for Image Similarity Challenge Track 2. Required dependencies To begin with

Wenhao Wang 89 Jan 02, 2023
MEDS: Enhancing Memory Error Detection for Large-Scale Applications

MEDS: Enhancing Memory Error Detection for Large-Scale Applications Prerequisites cmake and clang Build MEDS supporting compiler $ make Build Using Do

Secomp Lab at Purdue University 34 Dec 14, 2022
3D Generative Adversarial Network

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling This repository contains pre-trained models and sampling

Chengkai Zhang 791 Dec 20, 2022
A library of extension and helper modules for Python's data analysis and machine learning libraries.

Mlxtend (machine learning extensions) is a Python library of useful tools for the day-to-day data science tasks. Sebastian Raschka 2014-2020 Links Doc

Sebastian Raschka 4.2k Jan 02, 2023
Specificity-preserving RGB-D Saliency Detection

Specificity-preserving RGB-D Saliency Detection Authors: Tao Zhou, Huazhu Fu, Geng Chen, Yi Zhou, Deng-Ping Fan, and Ling Shao. 1. Preface This reposi

Tao Zhou 35 Jan 08, 2023
Vector.ai assignment

fabio-tests-nisargatman Low Level Approach: ###Tables: continents: id*, name, population, area, createdAt, updatedAt countries: id*, name, population,

Ravi Pullagurla 1 Nov 09, 2021
Generating Digital Painting Lighting Effects via RGB-space Geometry (SIGGRAPH2020/TOG2020)

Project PaintingLight PaintingLight is a project conducted by the Style2Paints team, aimed at finding a method to manipulate the illumination in digit

651 Dec 29, 2022
PyTorch Implementation for "ForkGAN with SIngle Rainy NIght Images: Leveraging the RumiGAN to See into the Rainy Night"

ForkGAN with Single Rainy Night Images: Leveraging the RumiGAN to See into the Rainy Night By Seri Lee, Department of Engineering, Seoul National Univ

Seri Lee 52 Oct 12, 2022
Public repository created to store my custom-made tools for Just Dance (UbiArt Engine)

Woody's Just Dance Tools Public repository created to store my custom-made tools for Just Dance (UbiArt Engine) Development and updates Almost all of

Wodson de Andrade 8 Dec 24, 2022
Fast convergence of detr with spatially modulated co-attention

Fast convergence of detr with spatially modulated co-attention Usage There are no extra compiled components in SMCA DETR and package dependencies are

peng gao 135 Dec 07, 2022
Efficient and Scalable Physics-Informed Deep Learning and Scientific Machine Learning on top of Tensorflow for multi-worker distributed computing

Notice: Support for Python 3.6 will be dropped in v.0.2.1, please plan accordingly! Efficient and Scalable Physics-Informed Deep Learning Collocation-

tensordiffeq 74 Dec 09, 2022
DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation

DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation This project hosts the code for implementing the DCT-MASK algorithms

Alibaba Cloud 57 Nov 27, 2022
PyTorch Implementation of Vector Quantized Variational AutoEncoders.

Pytorch implementation of VQVAE. This paper combines 2 tricks: Vector Quantization (check out this amazing blog for better understanding.) Straight-Th

Vrushank Changawala 2 Oct 06, 2021
Code release for NeX: Real-time View Synthesis with Neural Basis Expansion

NeX: Real-time View Synthesis with Neural Basis Expansion Project Page | Video | Paper | COLAB | Shiny Dataset We present NeX, a new approach to novel

536 Dec 20, 2022
Pure python implementation reverse-mode automatic differentiation

MiniGrad A minimal implementation of reverse-mode automatic differentiation (a.k.a. autograd / backpropagation) in pure Python. Inspired by Andrej Kar

Kenny Song 76 Sep 12, 2022