1) Add .gitignore.

2) Update README and config.

.gitignore

+led / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# Misc. 
+.idea
+out
+/data
+

README.md

@@ -187,6 +187,12 @@ estimation.
 One can then modify the model to see which Lipschitz architectures obtain a tighter lower bound on the Wasserstein
 distance between the generator and empirical data distribution. 
 
+(warning) Unless the training conditions were exactly the same, the GANs obtained in the GAN training step 
+might be slightly different (due to high sensitivity of the training dynamics on initial conditions). Although the estimated 
+Wasserstein distances will be different in this case, the relative ordering and approximate ratios of the performance of 
+each Lipschitz architectures should be the the same as reported in the paper. We will remedy this by uploading a
+trained GAN checkpoint in a future commit. 
+
 ### Training LWGAN (Lipschitz WGANs)
 We can use the same WGAN training methodology, but build a discriminator network comprised of our methods (i.e. Bjorck 
 orthonormalized linear transformations and GroupSort activations)

lnets/tasks/gan/configs/train_GAN.json

@@ -11,7 +11,7 @@
 
   "dataset": "mnist",
   "split": "",
-  "epoch": 256,
+  "epoch": 50,
   "batch_size": 64,
   "input_size": 28,
 

lnets/tasks/gan/configs/train_LWGAN.json

@@ -11,7 +11,7 @@
 
   "dataset": "mnist",
   "split": "",
-  "epoch": 256,
+  "epoch": 50,
   "batch_size": 64,
   "input_size": 28,