> For the complete documentation index, see [llms.txt](https://isciml.s2labs.co/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://isciml.s2labs.co/command-line-options/isciml.md).

# 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.