"Ludwig is a toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code. http://uber.github.io/ludwig/"
ludwig train -mdf model.yaml --data_csv yld.csv
ludwig predict -m results/experiment_run_0/model --data_csv yld.csv
cat results_0/tags_predictions.csv
With 0
being the result folder number from the training run.
./predict.sh 0