Skip to content
No description, website, or topics provided.
Python
Branch: master
Clone or download

Latest commit

Files

Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
config add init experiments Feb 20, 2020
figures clean readme, remove some figures Mar 8, 2020
.gitignore Initial commit Feb 20, 2020
README.md update spring-mass system Mar 8, 2020
build_utils.py update spring-mass system Mar 8, 2020
models.py remove unused model class Mar 8, 2020
plot_utils.py update spring-mass system Mar 8, 2020
requirements.txt clean readme, remove some figures Mar 8, 2020
run_exp.py add init experiments Feb 20, 2020
systems.py update spring-mass system Mar 8, 2020

README.md

Variational Integrator Networks

Overview

Link to paper

Variational Integrator Networks for Physically Structured Embeddings

Run experiment

python run_exp.py root_dir model_name system_name observations num_train_traj num_train_steps seed
e.g.
python run_exp.py experiments VIN_VV pendulum pixels 1 60 1

Dependencies

  • tensorflow 2.1
  • tensorflow_probability
  • gin-config
  • see requirements.txt

Example: Ideal Pendulum, Noisy Observations

Setup

  • Train on 15s of observations (150 datapoints)
  • Test on noisless initial state, forecast for 10s

Recurrent Residual Network (Left) / Variational Integrator Network (Right)

Example: Ideal Pendulum, Pixel Observations

Setup

  • Train on 6s of 28x28 pixel observations (60 datapoints)
  • Infer latent initial state from 1s of data
  • Forecast for 10s, reconstruct latent path

Recurrent ResNet (Left) / VIN (Middle) / VIN on SO(2) Manifold (Right)

You can’t perform that action at this time.