Code for the paper "Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer" by David Berthelot, Colin Raffel, Aurko Roy, and Ian Goodfellow.
This is not an officially supported Google product.
sudo apt install virtualenv
cd <path_to_code>
virtualenv --system-site-packages env2
. env2/bin/activate
pip install -r requirements.txt
Choose a folder where to save the datasets, for example ~/Data
export AE_DATA=~/Data
python create_datasets.py
CUDA_VISIBLE_DEVICES=0 python acai.py \
--train_dir=TEMP \
--latent=16 --latent_width=2 --depth=16 --dataset=celeba32
All training from the paper can be found in folder runs
.
These are the maintained models:
runs/classify.sh
for examples.runs/cluster.sh
for examples.