basic example of how to use uber's deep learning tool ludwig.
- Python3
- VSCode/ Pycharm as development (IDE)
- Linux machine (Preferred)
to install ludwig follow this video tutorial link
NB: The model that is used in this tutorial may not work and you may find this error:
ludwig train: error: one of the arguments -md/--model definition -mdef/--model definition file is required
This link is good and has brief description which is worth reading.
NB:
- The model is added already inside the project.
- Make sure you have Python3 installed on your machine.
- Install ludwig on your machine.
we can train a deep learning model using the following command:
ludwig experiment \
--data_csv reuters-allcats.csv \
--model_definition_file model_definition.yaml
After training we can evaluate the predictions of the model using the following command:
ludwig predict \
--data_csv reuters-allcats.csv \
--model_path results/experiment_run_5/model/
Visualization
ludwig visualize \
--visualization learning_curves \
--training_statistics results/experiment_run_5/training_statistics.json