Metadata-Version: 2.4
Name: graxpert
Version: 3.2.0a0.dev4
Summary: GraXpert is an astronomical image processing program for extracting and removing gradients in the background of your astrophotos
Home-page: https://graxpert.com
Author: GraXpert Development Team
Author-email: info@graxpert.com
License: GPL-3.0
Project-URL: Source Code, https://github.com/geeksville/GraXpert
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: End Users/Desktop
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Astronomy
Classifier: Topic :: Scientific/Engineering :: Image Processing
Classifier: Topic :: Multimedia :: Graphics :: Editors
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: MacOS
Classifier: Operating System :: POSIX :: Linux
Classifier: Environment :: Win32 (MS Windows)
Classifier: Environment :: MacOS X
Classifier: Environment :: X11 Applications
Classifier: Natural Language :: English
Classifier: Natural Language :: German
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: ml-dtypes>=0.5.3
Requires-Dist: pillow>=11.3.0
Requires-Dist: appdirs
Requires-Dist: astropy>=6.1.7
Requires-Dist: astropy-iers-data>=0.2025.9.1.0.42.11
Requires-Dist: customtkinter>=5.2.2
Requires-Dist: imageio>=2.37.0
Requires-Dist: minio>=7.2.16
Requires-Dist: numpy==2.2.6
Requires-Dist: opencv-python-headless==4.11.0.86
Requires-Dist: PyKrige>=1.7.2
Requires-Dist: requests>=2.32.5
Requires-Dist: scikit-image>=0.25.2
Requires-Dist: scipy>=1.15.3
Requires-Dist: xisf>=0.9.5
Provides-Extra: cuda
Requires-Dist: onnxruntime-gpu[cuda,cudnn]==1.22.0; extra == "cuda"
Provides-Extra: rocm
Requires-Dist: onnxruntime-rocm==1.22.1; extra == "rocm"
Provides-Extra: directml
Requires-Dist: onnxruntime-directml; extra == "directml"
Provides-Extra: openvino
Requires-Dist: onnxruntime-openvino==1.22.0; extra == "openvino"
Requires-Dist: openvino>=2025.3.0; extra == "openvino"
Provides-Extra: cpuonly
Requires-Dist: onnxruntime>=1.22.1; extra == "cpuonly"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: project-url
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

<p align="center">
<img src="https://github.com/Steffenhir/GraXpert/blob/main/img/GraXpert_LOGO_Hauptvariante.png" width="500"/>
</p>

# WARNING: This is a test branch/pip build, you probably don't want it yet.
For the time being you a re better off with the install images from the graxpert
homepage! for questions regarding this test build contact kevinh@geeksville.com.

GraXpert is an astronomical image processing program for extracting and removing
gradients in the background of your astrophotos.  We provide several methods traditional
interpolation methods such as Radial Basis Functions (RBF), Splines and Kriging which require
the user to manually select sample points in the background of the image. Our newest addition
is an AI method which does not require any user input.

Original                     |  Gradients removed with AI
:-------------------------:|:-------------------------:
![Original](https://raw.githubusercontent.com/Steffenhir/GraXpert/main/img/NGC7000_original.jpg)   |  ![Gradients removed](https://raw.githubusercontent.com/Steffenhir/GraXpert/main/img/NGC7000_processed.jpg)
![Original](https://raw.githubusercontent.com/Steffenhir/GraXpert/main/img/LDN1235_original.jpg)   |  ![Gradients removed](https://raw.githubusercontent.com/Steffenhir/GraXpert/main/img/LDN1235_processed.jpg)


**Homepage:** [https://www.graxpert.com](https://www.graxpert.com)  
**Download:** [https://github.com/Steffenhir/GraXpert/releases/latest](https://github.com/Steffenhir/GraXpert/releases/latest)

# Cross-Platform Installation
We are currently testing an optional cross-platform system for installing graxpert - which allows much smaller installation images and automated download/updates.

We do this via the the python [pypi.org](https://pypi.org/project/graxpert/) repository 'app-store.'  This is particularly important if you'd like to have GPU acceleration support for non Nvidia GPUs.  To install via this mechanism:

1. Install [python](https://www.python.org/downloads/) runtime for your OS.  The default install should automatically include the python package manager 'pip'.
2. At a shell prompt type the correct flavor of graxpert to install for your needs.

FIXME, recommend directml for windows, FIXME for linux and FIXME for mac

* **pip install graxpert\[cuda\]** - Use this if you have an Nvidia GPU
* **pip install graxpert\[rocm\]** - Use this if you have an AMD GPU
* **pip install graxpert\[openvino\]** - Use this if you don't have an advanced GPU or don't know what you have (provides sizable acceleration on most modern Intel CPUs)
* **pip install graxpert\[directml\]** - Use this if you want the Windows DirectML acceleration (not as fast as the options above but widely supported and easy to install)
* **pip install graxpert\[cpuonly\]** - If you encounter bugs with any of our GPU versions, please file a bug and temporarily use this version (which excludes all GPU code)

If you are an advanced python user and know about the 'pipx' tool, we recommend that you use that tool instead of pip for installs.

# Legacy Installation
You can download the latest official release of GraXpert [here](https://github.com/Steffenhir/GraXpert/releases/latest). Select the correct version for your operating system. For macOS, we provide different versions
for Intel processors (x86_64) and for apple silicon (arm64).

**Windows:** After downloading the .exe file, you should be able to start it directly. \
**Linux:** Before you can start GraXpert, you have to make it executable by running ```chmod u+x ./GraXpert-linux``` \
**macOS:** After opening the .dmg file, simply drag the GraXpert icon into the applications folder. GraXpert can now be started from the applications folder.

# Command-Line Usage
GraXpert comes with a graphical user interface. However, the AI method which does not need the selection of any background sample points can also be executed from the command line.
Here are the available command-line arguments and their descriptions:

- -cmd [image_operation]: This flag indicates which AI model to use. Options are "background-extraction" (default) or "denoising".
- filename: The path of the unprocessed image (required).
- -output [output_file_name]: Specify the name of the output image (without file ending). Otherwise the image will be saved with the suffix '_GraXpert' added to the original file name.
- -preferences_file: Allows GraXpert commandline to run all extraction methods based on a preferences file that contains background grid points.
- -gpu: Set to 'false' in order to disable gpu acceleration during AI inference, otherwise set to 'true' to enable it.
- -ai_version [version]: Specify the version of the AI model to use. If not provided, it defaults to the latest available version. You can choose from locally available versions and remotely available versions.

Specific commands to each operation:

Background Extraction:
- -correction [type]: Select the background correction method. Options are "Subtraction" (default) or "Division."
- -smoothing [strength]: Adjust the strength of smoothing, ranging from 0.0 (no smoothing) to 1 (maximum smoothing).
- -bg: Also save the generated background model.

Denoising:
- -strength [value]: Adjust the strength of denoising, ranging from 0.0 (minimum) to 1 (maximum). Default: "0.5".
- -batch_size [value]: Number of image tiles which Graxpert will denoise in parallel. Be careful: increasing this value might result in out-of-memory errors. Valid Range: 1..32, default: "4".

## Examples
The following examples show how GraXpert can be used from the command line in Windows. For Linux and macOS, you have to do the following replacements:

**Linux:** Replace GraXpert-win64.exe by GraXpert-linux \
**macOS:** Replace GraXpert-win64.exe by GraXpert.app/Contents/MacOS/GraXpert

Basic Usage:
```
GraXpert-win64.exe my_image.fits
```

Specify AI Model Version '1.1', correction type 'Division', smoothing '0.1', and save background model:
```
GraXpert-win64.exe my_image.fits -ai_version 1.1 -correction Division -smoothing 0.1 -bg
```

# Installation for Developers
This guide will help you get started with development of GraXpert on Windows, Linux, and macOS. Follow these steps to clone the repository, create a virtual environment with Python, install the required packages, and run GraXpert from the source code.

## Clone the repository
Open your terminal or command prompt and use git to clone the GraXpert repository:
```
git clone https://github.com/Steffenhir/GraXpert
cd GraXpert
```
## Option 1: Manual developer environment setup

### Setup the Virtual Environment
We recommend using a virtual environment to isolate the project's dependencies. Ensure you have Python>=3.10 installed on your system before proceeding. Here's how to set up a virtual environment with Python:
Windows:
```
# Create a new virtual environment with Python 3.10
python -m venv graxpert-env

# Activate the virtual environment
graxpert-env\Scripts\activate
```

Linux and macOS:
```
# Create a new virtual environment with Python 3.10
python3 -m venv graxpert-env

# Activate the virtual environment
source graxpert-env/bin/activate
```

### Install required packages
All the requirements can be found in the requirements.txt file. You can install them with:

Windows and Linux:
```
pip install -r requirements.txt
```

macOS:
```
pip3 install -r requirements.txt

"""
For macOS, we have to install tkinter separately.
We use the version provided by brew because it is newer
and solves issues with macOS Sonoma. Please use the version matching with your Python version.
"""
brew install python-tk@3.10
```

## Option 2: Automatic setup with devcontainers
This project includes an (optional) [devcontainer](https://containers.dev/) configuration.  If you are using any editor with built-in devcontainer support (i.e. VScode or jetbrains etc...), you should get prompted to "Reopen in a devcontainer?"

If you choose to use a devcontainer a docker (or podman) based container environment will be created for your development.  This environment appears to be a Debian machine (regardless of your host-OS).  All windowing/file/network operations are forwarded through your host.

This provides a nice 'guaranteed' repeatable build/debug environment for all developers.

## Running GraXpert
Once you have set up the virtual environment (using either of the options above), you can start GraXpert in your shell:

```
python -m graxpert.main
```


