Code for the Paper: Alexandra Lindt and Emiel Hoogeboom.

Overview

Discrete Denoising Flows

This repository contains the code for the experiments presented in the paper Discrete Denoising Flows [1].

To give a short overview on the architecture of the implementation:

  • main.py: Starting point and configuration of experiments
  • training.py: Training logic
  • visualization_.py: Functions for plotting samples from trained model
  • model/categorical_prior.py: Prior distribution and splitpriors
  • model/model.py: Overall model object (Discrete Denoising Flow and prior)
  • model/flow.py: Discrete Denoising Flow object
  • model/flow_layers.py: Implementations of
    • Discrete denoising coupling layer (including the conditional permutation operation introduced in the paper)
    • Permutation layer
    • Squeeze layer
  • model/network.py: Implementation of DenseNet and simple MLP
  • data/*: Logic for loading Eight Gaussians, MNIST and Cityscapes datasets

Usage

For each of the following commands, the results are saved in the folder ./results.

8 Gaussians

To test Discrete Denoising Flows with limited computational resources, run the 8 Gaussian toy data experiment. It takes only a few minutes to execute on a 12 GB RAM laptop.

python main.py --dataset='8gaussians' --k_sort=91 --n_hidden_nn=256 --net_epochs=30 --prior_epochs=20

Binary MNIST

For the experiment on Binary MNIST run

python main.py --dataset='mnist' --k_sort=2 --n_hidden_nn=512 --densenet_depth=10 --net_epochs=100 --prior_epochs=30 

For running the experiment without splitpriors, set the flag --with_splitprior False.

Cityscapes

For this experiment, it is necessary to download the Cityscapes data set. For preprocessing, download from this repository the data_to_npy.py and cityscapes.py files that perform the conversion of the original data. This creates three .npy files that should be placed in ./data/cityscapes/preprocessed. Then run

python main.py --dataset='cityscapes' --k_sort=4 --n_hidden_nn=512 --densenet_depth=15 --net_epochs=100 --prior_epochs=30 

Again, for running the experiment without splitpriors, set the flag --with_splitprior False.

Acknowledgements

We gratefully acknowledge the financial support of Robert Bosch GmbH.

References

[1] Alexandra Lindt and Emiel Hoogeboom. "Discrete Denoising Flows." ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (2021).

Owner
Alexandra Lindt
Alexandra Lindt
Code release for the paper “Worldsheet Wrapping the World in a 3D Sheet for View Synthesis from a Single Image”, ICCV 2021.

Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image This repository contains the code for the following paper: R. Hu,

Meta Research 37 Jan 04, 2023
Spatial Transformer Nets in TensorFlow/ TensorLayer

MOVED TO HERE Spatial Transformer Networks Spatial Transformer Networks (STN) is a dynamic mechanism that produces transformations of input images (or

Hao 36 Nov 23, 2022
Official implementation of YOGO for Point-Cloud Processing

You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module By Chenfeng Xu, Bohan Zhai, Bichen Wu, T

Chenfeng Xu 67 Dec 20, 2022
The code for the NSDI'21 paper "BMC: Accelerating Memcached using Safe In-kernel Caching and Pre-stack Processing".

BMC The code for the NSDI'21 paper "BMC: Accelerating Memcached using Safe In-kernel Caching and Pre-stack Processing". BibTex entry available here. B

Orange 383 Dec 16, 2022
The FIRST GANs-based omics-to-omics translation framework

OmiTrans Please also have a look at our multi-omics multi-task DL freamwork 👀 : OmiEmbed The FIRST GANs-based omics-to-omics translation framework Xi

Xiaoyu Zhang 6 Dec 14, 2022
A complete speech segmentation system using Kaldi and x-vectors for voice activity detection (VAD) and speaker diarisation.

bbc-speech-segmenter: Voice Activity Detection & Speaker Diarization A complete speech segmentation system using Kaldi and x-vectors for voice activit

BBC 16 Oct 27, 2022
Official codebase for running the small, filtered-data GLIDE model from GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

GLIDE This is the official codebase for running the small, filtered-data GLIDE model from GLIDE: Towards Photorealistic Image Generation and Editing w

OpenAI 2.9k Jan 04, 2023
Code for ICLR 2021 Paper, "Anytime Sampling for Autoregressive Models via Ordered Autoencoding"

Anytime Autoregressive Model Anytime Sampling for Autoregressive Models via Ordered Autoencoding , ICLR 21 Yilun Xu, Yang Song, Sahaj Gara, Linyuan Go

Yilun Xu 22 Sep 08, 2022
mPose3D, a mmWave-based 3D human pose estimation model.

mPose3D, a mmWave-based 3D human pose estimation model.

KylinChen 35 Nov 08, 2022
Code for the paper: Sketch Your Own GAN

Sketch Your Own GAN Project | Paper | Youtube | Slides Our method takes in one or a few hand-drawn sketches and customizes an off-the-shelf GAN to mat

677 Dec 28, 2022
Create and implement a deep learning library from scratch.

In this project, we create and implement a deep learning library from scratch. Table of Contents Deep Leaning Library Table of Contents About The Proj

Rishabh Bali 22 Aug 23, 2022
Pre-trained BERT Models for Ancient and Medieval Greek, and associated code for LaTeCH 2021 paper titled - "A Pilot Study for BERT Language Modelling and Morphological Analysis for Ancient and Medieval Greek"

Ancient Greek BERT The first and only available Ancient Greek sub-word BERT model! State-of-the-art post fine-tuning on Part-of-Speech Tagging and Mor

Pranaydeep Singh 22 Dec 08, 2022
Weakly Supervised Text-to-SQL Parsing through Question Decomposition

Weakly Supervised Text-to-SQL Parsing through Question Decomposition The official repository for the paper "Weakly Supervised Text-to-SQL Parsing thro

14 Dec 19, 2022
Have you ever wondered how cool it would be to have your own A.I

Have you ever wondered how cool it would be to have your own A.I. assistant Imagine how easier it would be to send emails without typing a single word, doing Wikipedia searches without opening web br

Harsh Gupta 1 Nov 09, 2021
Inferring Lexicographically-Ordered Rewards from Preferences

Inferring Lexicographically-Ordered Rewards from Preferences Code author: Alihan Hüyük ([e

Alihan Hüyük 1 Feb 13, 2022
codebase for "A Theory of the Inductive Bias and Generalization of Kernel Regression and Wide Neural Networks"

Eigenlearning This repo contains code for replicating the experiments of the paper A Theory of the Inductive Bias and Generalization of Kernel Regress

Jamie Simon 45 Dec 02, 2022
Code in PyTorch for the convex combination linear IAF and the Householder Flow, J.M. Tomczak & M. Welling

VAE with Volume-Preserving Flows This is a PyTorch implementation of two volume-preserving flows as described in the following papers: Tomczak, J. M.,

Jakub Tomczak 87 Dec 26, 2022
Demo code for paper "Learning optical flow from still images", CVPR 2021.

Depthstillation Demo code for "Learning optical flow from still images", CVPR 2021. [Project page] - [Paper] - [Supplementary] This code is provided t

130 Dec 25, 2022
An implementation for Neural Architecture Search with Random Labels (CVPR 2021 poster) on Pytorch.

Neural Architecture Search with Random Labels(RLNAS) Introduction This project provides an implementation for Neural Architecture Search with Random L

18 Nov 08, 2022
Expressive Power of Invariant and Equivaraint Graph Neural Networks (ICLR 2021)

Expressive Power of Invariant and Equivaraint Graph Neural Networks In this repository, we show how to use powerful GNN (2-FGNN) to solve a graph alig

Marc Lelarge 36 Dec 12, 2022