The library was created in order to extend Cleverhans models.
The main goal is to ease the design process for new models by introducing the
train_graph.py abstraction and other layers such as
The inspiration comes from Cleverhans. For the moment all models are extended to use name_scopes. Moreover, new architectures will be implemented in the
pip install pip install dnnmodels
git clone https://github.com/NullConvergence/dnnmodels
pip install -e ./dnnmodels
- At the moment there is only one example: