After you have compiled the configuration file following the commentary in template_cnn.yml you can execute the data preprocessing pipeline.
python preprocess_ds.py -f ../conf/your_conf_file.ymlTo pre-clean the processed dataset using a trained cnn-cleaner you trained or that was provided by this project.
python preclean_ds.py -f ../conf/your_conf_file.ymlAlternatively you can submit a job to Slurm if available to you.
python slurmjobs.py -f ../conf/your_conf_file.yml -s preprocess_dsor
python slurmjobs.py -f ../conf/your_conf_file.yml -s preclean_ds