Giter VIP home page Giter VIP logo

mfm's Introduction

Code and data to replicate experiments in "Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows".

Run experiments:

example="4-mode"
echo "$example..."

python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps -1
python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps 1000
python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps 100
python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps 100 --hutch
python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps 10
python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps 10 --hutch
python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps 1
python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps 1 --hutch

python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps 10 --do_fab
python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps 10 --do_dds
python3 multi_modal.py --example $example --learning_iter 1000 --mcmc_per_flow_steps 10 --do_flowmc


example="gaussian-mixture"
echo "$example..."

python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps -1
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10000
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 1000
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 1000 --hutch
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 100
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 100 --hutch
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10 --hutch

python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10 --do_fab
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10 --do_dds
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10 --do_flowmc


example="phi-four"
echo "$example..."

python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10000 --hutch
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 1000
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 1000 --hutch
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 100
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 100 --hutch

python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10 --do_fab
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10 --do_dds
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10 --do_flowmc


example="pines"
echo "$example..."

python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10000 --hutch
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 1000
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 1000 --hutch
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 100
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 100 --hutch

python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10 --do_fab
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10 --do_dds
python3 multi_modal.py --example $example --learning_iter 10000 --mcmc_per_flow_steps 10 --do_flowmc

mfm's People

Contributors

albcab avatar

Stargazers

yao teng avatar Tao Hu avatar aspirinliang avatar Thibeau Wouters avatar Louis Popi avatar  avatar  avatar Jed Homer avatar Kaze Wong avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.