Skip to content
PyTorch code accompanying our paper on Maximum Entropy Generators for Energy-Based Models
Branch: master
Clone or download
Latest commit 3b6535d Jan 23, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data
networks cleaning up code Jan 21, 2019
scripts
.gitignore major codebase update Sep 26, 2018
README.md

README.md

Maximum Entropy Generators for Energy-Based Models

All experiments have tensorboard visualizations for samples / density / train curves etc.

  1. To run the toy data experiments:
python scripts/train/ebm_toy.py --dataset swissroll --save_path logs/swissroll
  1. To run the discrete mode collapse experiment:
python scripts/train/ebm_mnist.py --save_path logs/mnist_3 --n_stack 3

This requires the pretrained mnist classifier:

python scripts/train/mnist_classifier.py
  1. To run the CIFAR image generation experiment:
python scripts/train/ebm_cifar.py --save_path logs/cifar

To run the MCMC evalulations on CIFAR data:

python scripts/test/eval_metrics_cifar --load_path logs/cifar --n_samples 50000 --mcmc_iters 5 --temp .01

NOTE: This requires cloning the TTUR repo in the current working directory (https://github.com/bioinf-jku/TTUR).

  1. To run the CelebA image generation experiments:
python scripts/train/ebm_celeba.py --save_path logs/celeba
You can’t perform that action at this time.
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session.