Command Line Interface Reference

cov3d

cov3d [OPTIONS] COMMAND [ARGS]...

Options

-v, --version: Prints the current version.

--install-completion <install_completion>

Install completion for the specified shell.

Options: bash | zsh | fish | powershell | pwsh

--show-completion <show_completion>

Show completion for the specified shell, to copy it or customize the installation.

Options: bash | zsh | fish | powershell | pwsh

bibliography

cov3d bibliography [OPTIONS]

bibtex

cov3d bibtex [OPTIONS]

infer

cov3d infer [OPTIONS]

Options

--gpu, --no-gpu

Whether or not to use a GPU for processing if available.

Default: True

--mc-samples <mc_samples>

The number of Monte Carlo samples of the results to get.

Default: 0

--mc-dropout, --no-mc-dropout

Whether or not to use Monte Carlo dropout if doing MC sampling.

Default: False

--pretrained <pretrained>: The location (URL or filepath) of a pretrained model.

--reload, --no-reload

Should the pretrained model be downloaded again if it is online and already present locally.

Default: False

--scan <scan>: A directory of a CT scan.

--scan-dir <scan_dir>: A directory with CT scans in subdirectories. Subdirectories must start with ‘ct_scan’ or ‘test_ct_scan’.

--directory <directory>

--output-csv <output_csv>: A path to output the results as a CSV.

--output-mc <output_mc>: A path to output all MC inference runs as a PyTorch tensor.

--covid-txt <covid_txt>: A path to output the names of the predicted COVID positive scans.

--noncovid-txt <noncovid_txt>: A path to output the names of the predicted COVID negative scans.

--mild-txt <mild_txt>: A path to output the names of the predicted mild COVID scans.

--moderate-txt <moderate_txt>: A path to output the names of the predicted moderate COVID scans.

--severe-txt <severe_txt>: A path to output the names of the predicted severe COVID scans.

--critical-txt <critical_txt>: A path to output the names of the predicted critical COVID scans.

lr-finder

cov3d lr-finder [OPTIONS]

Options

--plot-filename <plot_filename>

--start-lr <start_lr>

Default: 1e-07

--end-lr <end_lr>

Default: 10

--iterations <iterations>

Default: 100

--fp16, --no-fp16

Whether or not the floating-point precision of learner should be set to 16 bit.

Default: True

--output-dir <output_dir>

The location of the output directory.

Default: ./outputs

--weight-decay <weight_decay>: The amount of weight decay. If None then it uses the default amount of weight decay in fastai.

--presence-smoothing <presence_smoothing>

Default: 0.1

--severity-smoothing <severity_smoothing>

Default: 0.1

--neighbour-smoothing, --no-neighbour-smoothing

Default: False

--mse, --no-mse

Default: False

--emd-weight <emd_weight>

Default: 0.1

--directory <directory>: The data directory.

--batch-size <batch_size>

The batch size.

Default: 4

--splits-csv <splits_csv>: The path to a file which contains the cross-validation splits.

--split <split>

The cross-validation split to use. The default (i.e. 0) is the original validation set.

Default: 0

--training-severity <training_severity>: The path to the training Excel file with severity information.

--validation-severity <validation_severity>: The path to the validation Excel file with severity information.

--width <width>

The width to convert the images to.

Default: 128

--height <height>: The height to convert the images to. If None, then it is the same as the width.

--depth <depth>

The depth of the 3d volume to interpolate to.

Default: 128

--normalize, --no-normalize

Whether or not to normalize the pixel data by the mean and std of the dataset.

Default: False

--severity-factor <severity_factor>

Default: 0.5

--flip, --no-flip

Default: False

--brightness <brightness>

Default: 0.0

--contrast <contrast>

Default: 0.0

--distortion, --no-distortion

Default: True

--autocrop, --no-autocrop

Default: True

--max-scans <max_scans>

Default: 0

--model-name <model_name>

Default: r3d_18

--pretrained, --no-pretrained

Default: True

--penultimate <penultimate>

Default: 512

--dropout <dropout>

Default: 0.5

--max-pool, --no-max-pool

Default: False

--severity-regression, --no-severity-regression

Default: False

--final-bias, --no-final-bias

Default: False

--fine-tune, --no-fine-tune

Default: False

--flatten, --no-flatten

Default: False

--even-stride, --no-even-stride

Default: False

--positional-encoding, --no-positional-encoding

Default: False

--cov3d-trained <cov3d_trained>

--severity-everything, --no-severity-everything

Default: False

show-batch

cov3d show-batch [OPTIONS]

Options

--output-path <output_path>: A location to save the HTML which summarizes the batch.

--directory <directory>: The data directory.

--batch-size <batch_size>

The batch size.

Default: 4

--splits-csv <splits_csv>: The path to a file which contains the cross-validation splits.

--split <split>

The cross-validation split to use. The default (i.e. 0) is the original validation set.

Default: 0

--training-severity <training_severity>: The path to the training Excel file with severity information.

--validation-severity <validation_severity>: The path to the validation Excel file with severity information.

--width <width>

The width to convert the images to.

Default: 128

--height <height>: The height to convert the images to. If None, then it is the same as the width.

--depth <depth>

The depth of the 3d volume to interpolate to.

Default: 128

--normalize, --no-normalize

Whether or not to normalize the pixel data by the mean and std of the dataset.

Default: False

--severity-factor <severity_factor>

Default: 0.5

--flip, --no-flip

Default: False

--brightness <brightness>

Default: 0.0

--contrast <contrast>

Default: 0.0

--distortion, --no-distortion

Default: True

--autocrop, --no-autocrop

Default: True

--max-scans <max_scans>

Default: 0

train

cov3d train [OPTIONS]

Options

--distributed, --no-distributed

If the learner is distributed.

Default: False

--fp16, --no-fp16

Whether or not the floating-point precision of learner should be set to 16 bit.

Default: True

--output-dir <output_dir>

The location of the output directory.

Default: ./outputs

--weight-decay <weight_decay>: The amount of weight decay. If None then it uses the default amount of weight decay in fastai.

--presence-smoothing <presence_smoothing>

Default: 0.1

--severity-smoothing <severity_smoothing>

Default: 0.1

--neighbour-smoothing, --no-neighbour-smoothing

Default: False

--mse, --no-mse

Default: False

--emd-weight <emd_weight>

Default: 0.1

--directory <directory>: The data directory.

--batch-size <batch_size>

The batch size.

Default: 4

--splits-csv <splits_csv>: The path to a file which contains the cross-validation splits.

--split <split>

The cross-validation split to use. The default (i.e. 0) is the original validation set.

Default: 0

--training-severity <training_severity>: The path to the training Excel file with severity information.

--validation-severity <validation_severity>: The path to the validation Excel file with severity information.

--width <width>

The width to convert the images to.

Default: 128

--height <height>: The height to convert the images to. If None, then it is the same as the width.

--depth <depth>

The depth of the 3d volume to interpolate to.

Default: 128

--normalize, --no-normalize

Whether or not to normalize the pixel data by the mean and std of the dataset.

Default: False

--severity-factor <severity_factor>

Default: 0.5

--flip, --no-flip

Default: False

--brightness <brightness>

Default: 0.0

--contrast <contrast>

Default: 0.0

--distortion, --no-distortion

Default: True

--autocrop, --no-autocrop

Default: True

--max-scans <max_scans>

Default: 0

--model-name <model_name>

Default: r3d_18

--pretrained, --no-pretrained

Default: True

--penultimate <penultimate>

Default: 512

--dropout <dropout>

Default: 0.5

--max-pool, --no-max-pool

Default: False

--severity-regression, --no-severity-regression

Default: False

--final-bias, --no-final-bias

Default: False

--fine-tune, --no-fine-tune

Default: False

--flatten, --no-flatten

Default: False

--even-stride, --no-even-stride

Default: False

--positional-encoding, --no-positional-encoding

Default: False

--cov3d-trained <cov3d_trained>

--severity-everything, --no-severity-everything

Default: False

--epochs <epochs>

The number of epochs.

Default: 20

--freeze-epochs <freeze_epochs>

The number of epochs to train when the learner is frozen and the last layer is trained by itself. Only if fine_tune is set on the app.

Default: 3

--learning-rate <learning_rate>

The base learning rate (when fine tuning) or the max learning rate otherwise.

Default: 0.0001

--project-name <project_name>: The name for this project for logging purposes.

--run-name <run_name>: The name for this particular run for logging purposes.

--run-id <run_id>: A unique ID for this particular run for logging purposes.

--notes <notes>: A longer description of the run for logging purposes.

--tag <tag>: A tag for logging purposes. Multiple tags can be added each introduced with –tag.

--wandb, --no-wandb

Whether or not to use ‘Weights and Biases’ for logging.

Default: False

--wandb-mode <wandb_mode>

The mode for ‘Weights and Biases’.

Default: online

--wandb-dir <wandb_dir>: The location for ‘Weights and Biases’ output.

--wandb-entity <wandb_entity>: An entity is a username or team name where you’re sending runs.

--wandb-group <wandb_group>: Specify a group to organize individual runs into a larger experiment.

--wandb-job-type <wandb_job_type>: Specify the type of run, which is useful when you’re grouping runs together into larger experiments using group.

--mlflow, --no-mlflow

Whether or not to use MLflow for logging.

Default: False

tune

cov3d tune [OPTIONS]

Options

--runs <runs>

The number of runs to attempt to train the model.

Default: 1

--engine <engine>

The optimizer to use to perform the hyperparameter tuning. Options: wandb, optuna, skopt.

Default: skopt

--id <id>

The ID of this hyperparameter tuning job. If using wandb, then this is the sweep id. If using optuna, then this is the storage. If using skopt, then this is the file to store the results.

Default

--name <name>

An informative name for this hyperparameter tuning job. If empty, then it creates a name from the project name.

Default

--method <method>

The sampling method to use to perform the hyperparameter tuning. By default it chooses the default method of the engine.

Default

--min-iter <min_iter>: The minimum number of iterations if using early termination. If left empty, then early termination is not used.

--seed <seed>: A seed for the random number generator.

--distributed, --no-distributed

If the learner is distributed.

Default: False

--fp16, --no-fp16

Whether or not the floating-point precision of learner should be set to 16 bit.

Default: True

--output-dir <output_dir>

The location of the output directory.

Default: ./outputs

--weight-decay <weight_decay>: The amount of weight decay. If None then it uses the default amount of weight decay in fastai.

--presence-smoothing <presence_smoothing>

Default: 0.1

--severity-smoothing <severity_smoothing>

Default: 0.1

--neighbour-smoothing, --no-neighbour-smoothing

Default: False

--mse, --no-mse

Default: False

--emd-weight <emd_weight>

Default: 0.1

--directory <directory>: The data directory.

--batch-size <batch_size>

The batch size.

Default: 4

--splits-csv <splits_csv>: The path to a file which contains the cross-validation splits.

--split <split>

The cross-validation split to use. The default (i.e. 0) is the original validation set.

Default: 0

--training-severity <training_severity>: The path to the training Excel file with severity information.

--validation-severity <validation_severity>: The path to the validation Excel file with severity information.

--width <width>

The width to convert the images to.

Default: 128

--height <height>: The height to convert the images to. If None, then it is the same as the width.

--depth <depth>

The depth of the 3d volume to interpolate to.

Default: 128

--normalize, --no-normalize

Whether or not to normalize the pixel data by the mean and std of the dataset.

Default: False

--severity-factor <severity_factor>

Default: 0.5

--flip, --no-flip

Default: False

--brightness <brightness>

Default: 0.0

--contrast <contrast>

Default: 0.0

--distortion, --no-distortion

Default: True

--autocrop, --no-autocrop

Default: True

--max-scans <max_scans>

Default: 0

--model-name <model_name>

Default: r3d_18

--pretrained, --no-pretrained

Default: True

--penultimate <penultimate>

Default: 512

--dropout <dropout>

Default: 0.5

--max-pool, --no-max-pool

Default: False

--severity-regression, --no-severity-regression

Default: False

--final-bias, --no-final-bias

Default: False

--fine-tune, --no-fine-tune

Default: False

--flatten, --no-flatten

Default: False

--even-stride, --no-even-stride

Default: False

--positional-encoding, --no-positional-encoding

Default: False

--cov3d-trained <cov3d_trained>

--severity-everything, --no-severity-everything

Default: False

--epochs <epochs>

The number of epochs.

Default: 20

--freeze-epochs <freeze_epochs>

The number of epochs to train when the learner is frozen and the last layer is trained by itself. Only if fine_tune is set on the app.

Default: 3

--learning-rate <learning_rate>

The base learning rate (when fine tuning) or the max learning rate otherwise.

Default: 0.0001

--project-name <project_name>: The name for this project for logging purposes.

--run-name <run_name>: The name for this particular run for logging purposes.

--run-id <run_id>: A unique ID for this particular run for logging purposes.

--notes <notes>: A longer description of the run for logging purposes.

--tag <tag>: A tag for logging purposes. Multiple tags can be added each introduced with –tag.

--wandb, --no-wandb

Whether or not to use ‘Weights and Biases’ for logging.

Default: False

--wandb-mode <wandb_mode>

The mode for ‘Weights and Biases’.

Default: online

--wandb-dir <wandb_dir>: The location for ‘Weights and Biases’ output.

--wandb-entity <wandb_entity>: An entity is a username or team name where you’re sending runs.

--wandb-group <wandb_group>: Specify a group to organize individual runs into a larger experiment.

--wandb-job-type <wandb_job_type>: Specify the type of run, which is useful when you’re grouping runs together into larger experiments using group.

--mlflow, --no-mlflow

Whether or not to use MLflow for logging.

Default: False

validate

cov3d validate [OPTIONS]

Options

--gpu, --no-gpu

Whether or not to use a GPU for processing if available.

Default: True

--pretrained <pretrained>: The location (URL or filepath) of a pretrained model.

--reload, --no-reload

Should the pretrained model be downloaded again if it is online and already present locally.

Default: False

--directory <directory>: The data directory.

--batch-size <batch_size>

The batch size.

Default: 4

--splits-csv <splits_csv>: The path to a file which contains the cross-validation splits.

--split <split>

The cross-validation split to use. The default (i.e. 0) is the original validation set.

Default: 0

--training-severity <training_severity>: The path to the training Excel file with severity information.

--validation-severity <validation_severity>: The path to the validation Excel file with severity information.

--width <width>

The width to convert the images to.

Default: 128

--height <height>: The height to convert the images to. If None, then it is the same as the width.

--depth <depth>

The depth of the 3d volume to interpolate to.

Default: 128

--normalize, --no-normalize

Whether or not to normalize the pixel data by the mean and std of the dataset.

Default: False

--severity-factor <severity_factor>

Default: 0.5

--flip, --no-flip

Default: False

--brightness <brightness>

Default: 0.0

--contrast <contrast>

Default: 0.0

--distortion, --no-distortion

Default: True

--autocrop, --no-autocrop

Default: True

--max-scans <max_scans>

Default: 0