All Projects → dfdazac → Wassdistance

dfdazac / Wassdistance

Licence: mit
Approximating Wasserstein distances with PyTorch

Projects that are alternatives of or similar to Wassdistance

Comp Genomics Class
Code and examples for JHU Computational Genomics class
Stars: ✭ 228 (-0.44%)
Mutual labels:  jupyter-notebook
Hamiltonian Nn
Code for our paper "Hamiltonian Neural Networks"
Stars: ✭ 229 (+0%)
Mutual labels:  jupyter-notebook
Installations mac ubuntu windows
Installations for Data Science. Anaconda, RStudio, Spark, TensorFlow, AWS (Amazon Web Services).
Stars: ✭ 231 (+0.87%)
Mutual labels:  jupyter-notebook
Fusenet
Deep fusion project of deeply-fused nets, and the study on the connection to ensembling
Stars: ✭ 230 (+0.44%)
Mutual labels:  jupyter-notebook
All Python Codes Of Ztm Course By Andrei Neagoie
Stars: ✭ 229 (+0%)
Mutual labels:  jupyter-notebook
Neural Network From Scratch
Ever wondered how to code your Neural Network using NumPy, with no frameworks involved?
Stars: ✭ 230 (+0.44%)
Mutual labels:  jupyter-notebook
Ssd scene text detection
Detect text in natural images with SSD, Single Shot Detection
Stars: ✭ 229 (+0%)
Mutual labels:  jupyter-notebook
Aotodata
朱小五写文章涉及到的数据分析,爬虫,源数据
Stars: ✭ 232 (+1.31%)
Mutual labels:  jupyter-notebook
Stat451 Machine Learning Fs20
STAT 451: Intro to Machine Learning @ UW-Madison (Fall 2020)
Stars: ✭ 230 (+0.44%)
Mutual labels:  jupyter-notebook
Imaginary Numbers Are Real
Code To Accompany YouTube Series Imaginary Numbers Are Real
Stars: ✭ 231 (+0.87%)
Mutual labels:  jupyter-notebook
Beakerx
Beaker Extensions for Jupyter Notebook
Stars: ✭ 2,594 (+1032.75%)
Mutual labels:  jupyter-notebook
Structuredinference
Structured Inference Networks for Nonlinear State Space Models
Stars: ✭ 230 (+0.44%)
Mutual labels:  jupyter-notebook
Machine Learning By Andrew Ng In Python
Documenting my python implementation of Andrew Ng's Machine Learning course
Stars: ✭ 231 (+0.87%)
Mutual labels:  jupyter-notebook
Mydatascienceportfolio
Applying Data Science and Machine Learning to Solve Real World Business Problems
Stars: ✭ 227 (-0.87%)
Mutual labels:  jupyter-notebook
Stylegan2 Face Modificator
Simple Encoder, Generator and Face Modificator with StyleGAN2
Stars: ✭ 232 (+1.31%)
Mutual labels:  jupyter-notebook
Movie Plots By Genre
Movie plots by genre tutorial at PyData Berlin 2016
Stars: ✭ 230 (+0.44%)
Mutual labels:  jupyter-notebook
Nlp made easy
Explains nlp building blocks in a simple manner.
Stars: ✭ 232 (+1.31%)
Mutual labels:  jupyter-notebook
Learn Statistical Learning Method
Implementation of Statistical Learning Method, Second Edition.《统计学习方法》第二版,算法实现。
Stars: ✭ 228 (-0.44%)
Mutual labels:  jupyter-notebook
Introduction To Python
Python is an interpreted, high-level, general-purpose programming language. Created by Guido van Rossum and first released in 1991, Python's design philosophy emphasizes code readability with its notable use of significant white space. (This repository contains Python 3 Code)
Stars: ✭ 232 (+1.31%)
Mutual labels:  jupyter-notebook
Dagmm
My attempt at reproducing the paper Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
Stars: ✭ 231 (+0.87%)
Mutual labels:  jupyter-notebook

Approximating Wasserstein distances with PyTorch

Repository for the blog post on Wasserstein distances.

Update (July, 2019): I'm glad to see many people have found this post useful. Its main purpose is to introduce and illustrate the problem. To apply these ideas to large datasets and train on GPU, I highly recommend the GeomLoss library, which is optimized for this.

Instructions

Create a conda environment with all the requirements (edit environment.yml if you want to change the name of the environment):

conda env create -f environment.yml

Activate the environment

source activate pytorch

Open the notebook to reproduce the results:

jupyter notebook
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].