Distributional Sliced-Wasserstein distance code

Related tags

Deep LearningDSW
Overview

Distributional Sliced Wasserstein distance

This is a pytorch implementation of the paper "Distributional Sliced-Wasserstein and Applications to Generative Modeling". The work was done during the residency at VinAI Research, Hanoi, Vietnam.

Requirement

  • python3.6
  • pytorch 1.3
  • torchvision
  • numpy
  • tqdm

Train on MNIST and FMNIST

python mnist.py \
    --datadir='./' \
    --outdir='./result' \
    --batch-size=512 \
    --seed=16 \
    --p=2 \
    --lr=0.0005 \
    --dataset='MNIST'
    --model-type='DSWD'\
    --latent-size=32 \ 
model-type in (SWD|MSWD|DSWD|GSWD|DGSWD|JSWD|JMSWD|JDSWD|JGSWD|JDGSWD|MGSWNN|JMGSWNN|MGSWD|JMGSWD)

Options for Sliced distances (number of projections used to approximate the distances)

--num-projection=1000

Options for Max Sliced-Wasserstein distance and Distributional distances (number of gradient steps for find the max slice or the optimal push-forward function):

--niter=10

Options for Distributional Sliced-Wasserstein Distance and Distributional Generalized Sliced-Wasserstein Distance (regularization strength)

--lam=10

Options for Generalized Wasserstein Distance (using circular function for Generalized Radon Transform)

--r=1000;\
--g='circular'

Train on CELEBA and CIFAR10 and LSUN

python main.py \
    --datadir='./' \
    --outdir='./result' \
    --batch-size=512 \
    --seed=16 \
    --p=2 \
    --lr=0.0005 \
    --model-type='DSWD'\
    --dataset='CELEBA'
    --latent-size=100 \ 
model-type in (SWD|MSWD|DSWD|GSWD|DGSWD|CRAMER)

Options for Sliced distances (number of projections used to approximate the distances)

--num-projection=1000

Options for Max Sliced-Wasserstein distance and Distributional distances (number of gradient steps for find the max slice or the optimal push-forward function):

--niter=1

Options for Distributional Sliced-Wasserstein Distance and Distributional Generalized Sliced-Wasserstein Distance (regularization strength)

--lam=1

Options for Generalized Wasserstein Distance (using circular function for Generalized Radon Transform)

--r=1000;\
--g='circular'

Some generated images

MNIST generated images

MNIST

CELEBA generated images

MNIST

LSUN generated images

MNIST

Owner
VinAI Research
VinAI Research
[cvpr22] Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation

PS-MT [cvpr22] Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation by Yuyuan Liu, Yu Tian, Yuanhong Chen, Fengbei Liu, Vasile

Yuyuan Liu 132 Jan 03, 2023
DC540 hacking challenge 0x00005a.

dc540-0x00005a DC540 hacking challenge 0x00005a. PROMOTIONAL VIDEO - WATCH NOW HERE ON YOUTUBE CRITICAL PART 5A VIDEO - WATCH NOW HERE ON YOUTUBE Prio

Kevin Thomas 3 May 09, 2022
Edge Restoration Quality Assessment

ERQA - Edge Restoration Quality Assessment ERQA - a full-reference quality metric designed to analyze how good image and video restoration methods (SR

MSU Video Group 27 Dec 17, 2022
DFFNet: An IoT-perceptive Dual Feature Fusion Network for General Real-time Semantic Segmentation

DFFNet Paper DFFNet: An IoT-perceptive Dual Feature Fusion Network for General Real-time Semantic Segmentation. Xiangyan Tang, Wenxuan Tu, Keqiu Li, J

4 Sep 23, 2022
Fewshot-face-translation-GAN - Generative adversarial networks integrating modules from FUNIT and SPADE for face-swapping.

Few-shot face translation A GAN based approach for one model to swap them all. The table below shows our priliminary face-swapping results requiring o

768 Dec 24, 2022
Source code for "UniRE: A Unified Label Space for Entity Relation Extraction.", ACL2021.

UniRE Source code for "UniRE: A Unified Label Space for Entity Relation Extraction.", ACL2021. Requirements python: 3.7.6 pytorch: 1.8.1 transformers:

Wang Yijun 109 Nov 29, 2022
shufflev2-yolov5:lighter, faster and easier to deploy

shufflev2-yolov5: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size

pogg 1.5k Jan 05, 2023
ProjectOxford-ClientSDK - This repo has moved :house: Visit our website for the latest SDKs & Samples

This project has moved 🏠 We heard your feedback! This repo has been deprecated and each project has moved to a new home in a repo scoped by API and p

Microsoft 970 Nov 28, 2022
Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).

Microsoft365_devicePhish Abusing Microsoft 365 OAuth Authorization Flow for Phishing Attack This is a simple proof-of-concept script that allows an at

Alex 236 Dec 21, 2022
Code and data for "TURL: Table Understanding through Representation Learning"

TURL This Repo contains code and data for "TURL: Table Understanding through Representation Learning". Environment and Setup Data Pretraining Finetuni

SunLab-OSU 63 Nov 23, 2022
AFL binary instrumentation

E9AFL --- Binary AFL E9AFL inserts American Fuzzy Lop (AFL) instrumentation into x86_64 Linux binaries. This allows binaries to be fuzzed without the

242 Dec 12, 2022
pytorch implementation of ABC : Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning

ABC:Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning, NeurIPS 2021 pytorch implementation of ABC : Auxiliary Balanced Class

Hyuck Lee 25 Dec 22, 2022
How to train a CNN to 99% accuracy on MNIST in less than a second on a laptop

Training a NN to 99% accuracy on MNIST in 0.76 seconds A quick study on how fast you can reach 99% accuracy on MNIST with a single laptop. Our answer

Tuomas Oikarinen 42 Dec 10, 2022
Multi-Template Mouse Brain MRI Atlas (MBMA): both in-vivo and ex-vivo

Multi-template MRI mouse brain atlas (both in vivo and ex vivo) Mouse Brain MRI atlas (both in-vivo and ex-vivo) (repository relocated from the origin

8 Nov 18, 2022
FIRA: Fine-Grained Graph-Based Code Change Representation for Automated Commit Message Generation

FIRA is a learning-based commit message generation approach, which first represents code changes via fine-grained graphs and then learns to generate commit messages automatically.

Van 21 Dec 30, 2022
基于pytorch构建cyclegan示例

cyclegan-demo 基于Pytorch构建CycleGAN示例 如何运行 准备数据集 将数据集整理成4个文件,分别命名为 trainA, trainB:训练集,A、B代表两类图片 testA, testB:测试集,A、B代表两类图片 例如 D:\CODE\CYCLEGAN-DEMO\DATA

Koorye 3 Oct 18, 2022
Code for Learning to Segment The Tail (LST)

Learning to Segment the Tail [arXiv] In this repository, we release code for Learning to Segment The Tail (LST). The code is directly modified from th

47 Nov 07, 2022
Python implementation of ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images, AAAI2022.

ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images Binh M. Le & Simon S. Woo, "ADD:

2 Oct 24, 2022
DataCLUE: 国内首个以数据为中心的AI测评(含模型分析报告)

DataCLUE: A Benchmark Suite for Data-centric NLP You can get the english version of README. 以数据为中心的AI测评(DataCLUE) 内容导引 章节 描述 简介 介绍以数据为中心的AI测评(DataCLUE

CLUE benchmark 135 Dec 22, 2022
EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers

EntityQuestions This repository contains the EntityQuestions dataset as well as code to evaluate retrieval results from the the paper Simple Entity-ce

Princeton Natural Language Processing 119 Sep 28, 2022