ML FW evaluation - jniedzie/SVJanalysis_wiki GitHub Wiki

After the training is done, ROOT files containing "evaluation objects", e.g. ROCs, ROC AUCs, training metrics evolution etc...

python prepareEvaluationObjects.py -c configs/ae_default.py <evaluation_flags>

Replace <evaluation_flags> by the flags you need to produce the evaluation objects you want. You can find a description of all evaluation flags with python prepareEvaluationObjects.py -h.

Important note:
A script tailored for the NAE is set up to perform training, evaluation and plotting! See run_nae_training_evaluation_and_plots_example.sh. You can find example usage in this script.