repository for the ab dcnn project
the code is programmed in Python 3.6. for help on installing python 3.6 on your system, we refer to using conda (https://docs.conda.io/en/latest/).
To install the packages required to run the code, run:
pip install -r requirements.txt
Most of the code is shown as jupyter notebook tutorials, and will run quickly on most modern systems. The cross-validated fitting procedure however, was implement on a high performance computing cluster and takes several days of computation for all DCNN layers.
To start, look at 'Plot_results.ipynb' in the /code folder, where each step is described.
To run Plot_results.ipynb online without having to download anything to your computer, click:
And go to code/Plot_results.ipynb