Metadata-Version: 2.4
Name: abismal
Version: 0.0.7
Summary: Stochastic merging for diffraction data.
Author-email: "Kevin M. Dalton" <kmdalton@slac.stanford.edu>
License: MIT
Project-URL: Repository, https://github.com/rs-station/abismal
Project-URL: Issues, https://github.com/rs-station/abismal/issues
Requires-Python: <3.13,>=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: reciprocalspaceship>=0.9.16
Requires-Dist: tqdm
Requires-Dist: tensorflow-probability[tf]==0.25
Requires-Dist: tensorflow==2.18.0
Requires-Dist: matplotlib
Requires-Dist: seaborn
Requires-Dist: rs-booster
Requires-Dist: ray
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: pytest-cov; extra == "dev"
Requires-Dist: pytest-xdist; extra == "dev"
Provides-Extra: cuda
Requires-Dist: tensorflow[and-cuda]==2.18.0; extra == "cuda"
Dynamic: license-file

# abismal
**A**pproximate **B**ayesian **I**nference for **S**caling and **M**erging at **A**dvanced **L**ightsources

Scaling and merging for large diffraction datasets using stochastic variational inference and deep learning.

This project is under development. 


# Installation
First create a conda env with dials,
```bash
conda create -yn abismal -c conda-forge dials
conda activate abismal
```
Next install abismal. 
For the CPU version, run 

```bash
pip install --upgrade pip
pip install abismal
```

For NVIDIA CUDA support, we recommend you use the anaconda python distribution. The following will create a new conda environment and install abismal:

```bash
pip install --upgrade pip
pip install abismal[cuda]
```

You can now use abismal with GPU acceleration by running `conda activate abismal`. 
You can test GPU support by typing `abismal --list-devices`. 
