cli.rst

Command-Line Interface (CLI)

This package provides a single entry point for all of its applications using :ref:`Bob's unified CLI mechanism <bob.extension.cli>`. A list of available applications can be retrieved using:

Setup

A CLI application to list and check installed (raw) datasets.

List available datasets

Lists supported and configured raw datasets.

Check available datasets

Checks if we can load all files listed for a given dataset (all subsets in all protocols).

Preset Configuration Resources

A CLI application allows one to list, inspect and copy available configuration resources exported by this package.

Listing Resources

Available Resources

Here is a list of all resources currently exported.

Describing a Resource

Copying a Resource

You may use this command to locally copy a resource file so you can change it.

Running and Analyzing Experiments

These applications run a combined set of steps in one go. They work well with our preset :ref:`configuration resources <bob.ip.binseg.cli.config.list.all>`.

Running a Full Experiment Cycle

This command can run training, prediction, evaluation and comparison from a single, multi-step application.

Running Complete Experiment Analysis

This command can run prediction, evaluation and comparison from a single, multi-step application.

Single-Step Applications

These applications allow finer control over the experiment cycle. They also work well with our preset :ref:`configuration resources <bob.ip.binseg.cli.config.list.all>`, but allow finer control on the input datasets.

Training FCNs

Training creates of a new PyTorch_ model. This model can be used for evaluation tests or for inference.

Prediction with FCNs

Inference takes as input a PyTorch_ model and generates output probabilities as HDF5 files. The probability map has the same size as the input and indicates, from 0 to 1 (floating-point number), the probability of a vessel in that pixel, from less probable (0.0) to more probable (1.0).

FCN Performance Evaluation

Evaluation takes inference results and compares it to ground-truth, generating a series of analysis figures which are useful to understand model performance.

Performance Comparison

Performance comparison takes the performance evaluation results and generate combined figures and tables that compare results of multiple systems.

Performance Difference Significance

Calculates the significance between results obtained through 2 systems on the same dataset.