isciml

isciml: Main Commands Overview

isciml is a powerful command-line tool designed for solving 3D non-invasive imaging problems using physics-informed AI. It offers a range of functionalities through its main commands, each serving a specific purpose in the workflow of model generation, data creation, training, and inference.

Usage

singularity exec isciml.sif isciml [OPTIONS] COMMAND [ARGS]...

Global Options

Option	Description
--help	Show the help message and exit.

Main Commands

generate-models

The generate-models command focuses on creating and manipulating the underlying models used in the imaging process. This includes:

• Creating mesh files

• Defining geometries (e.g., pipes, layers)

• Setting material properties (e.g., conductivity, permeability)

This command is crucial for setting up the physical model of your imaging scenario and should be used before generating response data.

generate

The generate command is used for creating synthetic data or response files based on the models created with generate-models. This may include generating:

• Electromagnetic field data

• Sensor responses

• Synthetic measurements

Use this command when you need to create input data for your AI models or simulations, based on the physical models you've defined.

train

The train command is used to train machine learning models on your data. This process involves:

• Specifying training data

• Defining model architecture

• Setting training parameters

• Executing the training process

Use this command when you're ready to train your AI model on your prepared dataset.

inference

The inference command is used to apply trained models to new data for prediction or analysis. This typically involves:

• Loading a trained model

• Providing input data

• Generating predictions or insights

Use this command when you have a trained model and want to apply it to new, unseen data.

Getting Started

To get started with isciml, you typically follow this workflow:

1. Use generate-models to create your physical model.

2. Use generate to create synthetic response data based on your models.

3. Use train to train your AI model on the prepared data.

4. Use inference to apply your trained model to new data.

For detailed information on each command and its options, use the --help option:

singularity exec isciml.sif isciml COMMAND --help

This will display the specific options and usage for each main command.