Model

Command-line usage

This page provides documentation for command line tools.

pd-dwi

Usage:

pd-dwi [OPTIONS] COMMAND [ARGS]...

Options:

Name Type Description Default
--version boolean Show the version and exit. False
--help boolean Show this message and exit. False

pd-dwi list

Outputs list of pre-trained models that are available as part of the package.

Usage:

pd-dwi list [OPTIONS]

Options:

Name Type Description Default
--help boolean Show this message and exit. False

pd-dwi predict

Calculate model prediction for all subjects in input dataset.

MODEL_PATH is the location of the model to use.

Usage:

pd-dwi predict [OPTIONS]

Options:

Name Type Description Default
-m, --model file Location of saved model. _required
-d, --dataset directory Location of dataset. _required
-p, -probability boolean Retrieve prediction probability. False
-o, --output path Output path to store prediction results in. None
--help boolean Show this message and exit. False

pd-dwi score

Evaluate model performance on a given dataset.

Usage:

pd-dwi score [OPTIONS]

Options:

Name Type Description Default
-m, --model file Location of saved model. _required
-d, --dataset directory Location of dataset. _required
--help boolean Show this message and exit. False

pd-dwi train

Train a new model.

Usage:

pd-dwi train [OPTIONS]

Options:

Name Type Description Default
-d, --dataset directory Location of dataset. _required
-c, --config file Location of training configuration. _required
-o, --output path Location to save model after training completion. _required
--help boolean Show this message and exit. False