This code requires Python 3, and is implemented in Tensorflow.
Hopefully things should be fairly easy to run out of the box:
pip install -r requirements.txt mkdir data snapshot export PYTHONPATH="$PWD:$PYTHONPATH" scripts/svhn-mnist.sh
The provided script does the following things:
data/svhnin the process)
data/mnistin the process)
snapshot/lenet_svhn)
snapshot/adda_lenet_svhn_mnist)
scripts/svhn-mnist.shfor hyperparameters.
adda/models/lenet.py.
preprocessingfunction in
adda/models/model.py.
tools/train_adda.py.
adda/adversary.py.