Metadata-Version: 2.4
Name: ptyrad
Version: 0.1.0b10
Summary: PtyRAD: Ptychographic Reconstruction with Automatic Differentiation
Author-email: Chia-Hao Lee <cl2696@cornell.edu>
License-Expression: LGPL-3.0
Project-URL: Homepage, https://github.com/chiahao3/ptyrad
Project-URL: Repository, https://github.com/chiahao3/ptyrad
Project-URL: Issues, https://github.com/chiahao3/ptyrad/issues
Project-URL: Changelog, https://github.com/chiahao3/ptyrad/blob/main/CHANGELOG.md
Keywords: Ptychography
Classifier: Development Status :: 4 - Beta
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: accelerate
Requires-Dist: h5py
Requires-Dist: jupyter
Requires-Dist: matplotlib
Requires-Dist: optuna
Requires-Dist: pydantic
Requires-Dist: scikit-learn
Requires-Dist: scipy
Requires-Dist: tifffile
Requires-Dist: torch>=2.0
Requires-Dist: torchvision
Dynamic: license-file

# PtyRAD: Ptychographic Reconstruction with Automatic Differentiation
![PyPI - Version](https://img.shields.io/pypi/v/ptyrad)
[![Anaconda-Server Badge](https://anaconda.org/conda-forge/ptyrad/badges/version.svg)](https://anaconda.org/conda-forge/ptyrad)
[![Anaconda-Server Badge](https://anaconda.org/conda-forge/ptyrad/badges/latest_release_date.svg)](https://anaconda.org/conda-forge/ptyrad)
[![Anaconda-Server Badge](https://anaconda.org/conda-forge/ptyrad/badges/downloads.svg)](https://anaconda.org/conda-forge/ptyrad)
[![arXiv](https://img.shields.io/badge/arXiv-2505.07814-b31b1b.svg)](https://arxiv.org/abs/2505.07814)
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.15392805.svg)](https://doi.org/10.5281/zenodo.15392805)

[**Docs**](https://ptyrad.readthedocs.io/en/latest/index.html)
| [**Install Guide**](https://ptyrad.readthedocs.io/en/latest/installation.html)
| [**Quickstart**](https://ptyrad.readthedocs.io/en/latest/quickstart.html)
| [**Paper**](https://arxiv.org/abs/2505.07814)
| [**Youtube**](https://www.youtube.com/@ptyrad_official)

*PtyRAD* performs ptychographic reconstruction using an [automatic differention](https://en.wikipedia.org/wiki/Automatic_differentiation) (AD) framework powered by [*PyTorch*](https://pytorch.org/), which enables flexible and efficient implementation of gradient descent optimization. See our [arXiv paper](https://arxiv.org/abs/2505.07814) and the [Zenodo record](https://doi.org/10.5281/zenodo.15273176) for more information and demo datasets.

## Features
- Gradient descent algorithms (Adam, SGD, LBFGS, etc.)
- Mixed-state probe and object
- Position correction
- Position-dependent object tilt correction
- Interoperability with *PtychoShelves (fold_slice)* and *py4DSTEM*
- Streamlined preprocessing of cropping, padding, resampling, adding noises, and many more
- Hyperparameter tuning
- Multi-GPU reconstructions
- JIT compilation with torch.compile

## Recommended Tools
We recommend using [*Miniforge*](https://github.com/conda-forge/miniforge) for Python environment management, and  
[*Visual Studio Code*](https://code.visualstudio.com/Download) for code editing and execution.

## Major dependencies

* Python 3.10 or above
* PyTorch 2.0 or above
* While *PtyRAD* can run on CPU, GPU is strongly suggested for high-speed ptychographic reconstructions. 
    - *PtyRAD* supports both NVIDIA GPUs with CUDA and Apple Silicon (MPS)
* *PtyRAD* was tested on Windows, MacOS, and Linux

## Installation



We recommend installing *PtyRAD* using `pip` inside a fresh conda environment.

First, create and activate a new conda environment **(ptyrad)** with Python > 3.10:
```sh
conda create -n ptyrad python=3.12
conda activate ptyrad
```
> 💡 **Note:** After activating the environment, your terminal prompt should show **(ptyrad)** at the beginning, indicating that the environment is active.

Then install *PtyRAD* using:
```sh
pip install ptyrad
```

If you're using Windows with NVIDIA CUDA GPU, you will also need to install the GPU version of PyTorch with:
```sh
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu118 --force-reinstall
```

*PtyRAD* can also be installed via `conda`. For detailed instructions on installing *PtyRAD* on different machines or pinning specific CUDA versions, see [the installation guide](https://ptyrad.readthedocs.io/en/latest/installation.html).



### How do I check if my installed PtyRAD has the GPU support?
CUDA version, GPU support, and PyTorch build across platforms can be extremely confusing, so *PtyRAD* provides handy CLI tools to help check these information for you!

Once you activated `(ptyrad)` environment and installed *PtyRAD* via `pip insall ptyrad`, you'll have access to the following command:

```bash
# You can run this command anywhere from your terminal, as long as `ptyrad` is installed in the environment
ptyrad check-gpu
```

This command will print out relevant information of your CUDA information if available.

## Get Started with the Demo

> 💡 **Note:** Download the demo datasets and scripts from our [Box folder](https://cornell.box.com/s/n5balzf88jixescp9l15ojx7di4xn1uo), which contains `demo/` and other tutorial slides and videos.

Before running the demo, please check the following:
1. Demo datasets are downloaded and placed to the correct location under `demo/data/`
2. `(ptyrad)` environment is created and activated (in VS Code it's the "Select Kernel")
3. *PtyRAD* is installed in the `(ptyrad)` environment
   
Now you're ready to run a quick demo using one of two interfaces:

- **Interactive Jupyter interface (Recommended)**
 
    Use `demo/scripts/run_ptyrad_quick_example.ipynb` to quickly reconstruct the demo dataset in a Jupyter notebook

- **Command-line interface** (like your *Miniforge Prompt* terminal)
    ```bash
    # Here we assume working directory is set at `demo/`
    ptyrad run --params_path "params/tBL_WSe2_reconstruct.yml"
    ```

## Documentation
*PtyRAD* documentation is available at https://ptyrad.readthedocs.io/en/latest/index.html.

## Author

Chia-Hao Lee (cl2696@cornell.edu)

Developed at the Muller Group, Cornell University.

## Acknowledgments

Besides great support from the entire Muller group, this package gets inspiration from lots of community efforts, and specifically from the following packages. Some of the functions in *PtyRAD* are directly translated or modified from these packages as noted in their docstrings/comments to give explicit acknowledgment.
* [PtychoShelves](https://journals.iucr.org/j/issues/2020/02/00/zy5001/index.html)
* [fold_slice](https://github.com/yijiang1/fold_slice)
* [py4dstem](https://github.com/py4dstem/py4DSTEM)
* [adorym](https://github.com/mdw771/adorym)
* [SciComPty](https://www.mdpi.com/2410-3896/6/4/36)

## Other resources

* [ptycho-packages](https://github.com/chiahao3/ptycho-packages) lists many available ptychography packages
* [Cornell Box folder](https://cornell.box.com/s/n5balzf88jixescp9l15ojx7di4xn1uo) compiled by myself that keeps demo data, tutorial recordings, and slides for PtyRAD
* [Argonne Box folder](https://anl.box.com/s/f7lk410lf62rnia70fztd5l7n567btyv) compiled by Dr. Yi Jiang that holds tutorial slides of `fold_slice`
* [Blog post](https://chiahao-blog.super.site/posts/theory-algorithm-and-code-structure-of-ptychoshelves) written by myself that details the algorithms and code structure of `PtychoShelves` / `fold_slice`
