Skip to content
Generalized Loss-Sensitive Adversarial Learning implemented in Blocks
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
ali
experiments
scripts
README.md
theanorc

README.md

LSAL_generator_classifier

This is the code for Loss Sensitive Adversarial Learning with Manifold Margins. The base of the code has been borrowed from ALI [ALI]

Requirements

  • Blocks, development version
  • Fuel, development version

Setup

Clone the repository, then install with

$ pip install -e ALI

Downloading and converting the datasets

Set up your ~/.fuelrc file:

$ echo "data_path: \"<MY_DATA_PATH>\"" > ~/.fuelrc

Go to <MY_DATA_PATH>:

$ cd <MY_DATA_PATH>

Download the CIFAR-10 dataset:

$ fuel-download cifar10
$ fuel-convert cifar10
$ fuel-download cifar10 --clear

Download the SVHN format 2 dataset:

$ fuel-download svhn 2
$ fuel-convert svhn 2
$ fuel-download svhn 2 --clear

Download the CelebA dataset:

$ fuel-download celeba 64
$ fuel-convert celeba 64
$ fuel-download celeba 64 --clear

Training the models

Make sure you're in the repo's root directory.

CIFAR-10

$ THEANORC=theanorc python experiments/LSAL_cifar10.py

SVHN

$ THEANORC=theanorc python experiments/LSAL_svhn.py

CelebA

$ THEANORC=theanorc python experiments/LSAL_celeba_savemargins.py

Evaluating the models

Samples

$ THEANORC=theanorc scripts/sample [main_loop.tar]

e.g.

$ THEANORC=theanorc scripts/sample LSAL_cifar10.tar

Interpolations

$ THEANORC=theanorc scripts/interpolate [which_dataset] [main_loop.tar]

e.g.

$ THEANORC=theanorc scripts/interpolate celeba LSAL_celeba.tar

Reconstructions

$ THEANORC=theanorc scripts/reconstruct [which_dataset] [main_loop.tar]

e.g.

$ THEANORC=theanorc scripts/reconstruct cifar10 LSAL_cifar10.tar
You can’t perform that action at this time.