Metadata-Version: 2.4
Name: steren
Version: 0.0.1a0
Summary: A computer vision package for planetary GIS data and using neural networks
Author-email: Jack Rich <j.b.c.rich@pgr.reading.ac.uk>
License: MIT
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: typer
Requires-Dist: numpy
Requires-Dist: tqdm
Requires-Dist: pyaml
Requires-Dist: requests
Requires-Dist: beautifulsoup4
Requires-Dist: geopandas
Requires-Dist: shapely
Requires-Dist: rasterio
Requires-Dist: opencv-python
Requires-Dist: torch
Requires-Dist: torchvision

# Steren

**Steren** is an open-source Python package for analyzing planetary surfaces using artificial intelligence. It helps researchers and developers efficiently **search, download, slice, and detect features in planetary imagery.** 

<p align="center"> <img src="steren.png" alt="Steren Logo" width="50%"> </p>

## ✨ Features

### 🔎 Search
Discover and scan the web for the latest publicly available planetary datasets.

### ⬇️ Download
Easily retrieve and manage high-resolution planetary surface imagery.

### 🧠 Detect
Apply AI-powered object detection to identify features and structures across large planetary images.

### 🧩 Slice
Divide massive planetary surface images into smaller, manageable tiles for training, testing, and evaluation of AI models.

## 🌍 Use Cases

- Planetary science research  
- Surface feature detection (craters, rocks, anomalies)  
- Dataset preparation for machine learning  
- Automated analysis of remote sensing imagery  

---

## 🛠 Installation

### PyPI
```bash
pip install steren
```

### From Source (with Conda)
```bash
conda env create -f environment.yml
conda activate steren
git clone https://github.com/jbr819/steren.git
cd steren
pip install -e .
```


## 💻 CLI

Steren comes with a **straightforward command-line interface (CLI)**.  
You can quickly explore all available commands by running:

```bash
steren 
```


### Acknowledgements
Developed during a PhD student internship at the [Natural History Museum, London](https://www.nhm.ac.uk/) through the [BBSRC Professional Internships for PhD Students (PIPS)](https://bbsrc.ukri.org/training/placements/).
