Pixi init

README.md

@@ -1,115 +1,80 @@
-# GANrec: A GAN-based Data Reconstruction Framework
+# GANrec: A GAN-based data reconstruction framework
 
-# Overview
+## Overview
 
 GANrec is an data reconstruction framework that harnesses the power of Generative Adversarial Networks (GANs). While traditional reconstruction methods primarily rely on intricate algorithms to piece together fragmented data, GANrec employs the generative capabilities of GANs to reimagine and revitalize data reconstruction.
 
 Originally designed for the fields of tomography and phase retrieval, GANrec shines in its adaptability. With a provision to input the forward model, the framework can be flexibly adapted for complex data reconstruction processes across diverse applications.
 
-# Features
+## Features
 
 1. GAN-powered Reconstruction: At its core, GANrec employs GANs to assist in the reconstruction process, enabling more accurate and efficient results than conventional methods.
 2. Specialized for Tomography & Phase Retrieval: GANrec has been optimized for tomography and phase retrieval applications, ensuring precision and reliability in these domains.
 3. Modular Design: The framework's architecture allows users to provide their forward model, making it adaptable for various complex data reconstruction challenges.
 4. Efficient and Scalable: Built to handle large datasets, GANrec ensures that speed and efficiency are maintained without compromising the accuracy of reconstruction.
 
-# Installation
+## Installation
 
 This guide provides two ways to set up `ganrec`:
 - With Pixi (recommended, reproducible): default TensorFlow+CUDA backend with an optional PyTorch-only backend.
 - With Conda/pip (alternative): manual setup.
 
-## Pixi (recommended)
+### Pixi (recommended)
 
 Pixi manages environments and dependencies declaratively via `pyproject.toml`.
 
-- Default backend (TensorFlow with CUDA extras):
+- Default backend (TensorFlow with CUDA extras; no PyTorch):
 
 ```bash
 pixi install
-pixi run python -c "import tensorflow as tf; print(tf.__version__)"
 ```
 
 - Optional PyTorch backend (no TensorFlow):
 
 ```bash
 pixi -e pytorch install
-pixi -e pytorch run python -c "import torch; print(torch.__version__)"
 ```
 
-Notes:
-- The default Pixi environment installs TensorFlow with GPU support (via pip extra) and does not install PyTorch.
-- The `pytorch` Pixi environment installs PyTorch-only and does not install TensorFlow.
-- `ipython`/`ipykernel` are included so you can create a kernel for notebooks if needed.
-
-## Steps for General Users
-
-### 1. Create & Activate a Conda Environment
-Open your terminal or command prompt and create a new conda environment named `ganrec` with Python 3.11:
-
-```bash
-conda create --name ganrec python=3.11
-conda activate ganrec
-```
-
-### 2. Install Tensorflow OR Pytorch 
-Choose and install either TensorFlow or PyTorch based on your preference.
+Quick start with Pixi:
 
-For TensorFlow:
-```bash
-pip install tensorflow
-```
+1) Install Pixi (see https://pixi.sh)
+2) Clone this repo and enter it:
+   - git clone https://github.com/XYangXRay/ganrec.git && cd ganrec
+3) Install the default environment (TensorFlow):
+   - pixi install
+4) Or install the PyTorch environment only:
+   - pixi -e pytorch install
+5) Run examples:
+   - pixi run python examples/holography_tf.py
+   - pixi -e pytorch run python examples/tomography_torch.py
 
-For PyTorch (make sure to select the correct version for your system from the PyTorch website):
-```bash
-# Example command for installing PyTorch with CUDA support
-pip install torch torchvision torchaudio
-```
+Note: Environments are defined in `pyproject.toml` — `default` uses TensorFlow; `pytorch` uses PyTorch.
 
-### 3. Install 'ganrec' from PyPI
-Finally, install the ganrec package from PyPI:
-```bash
-pip install ganrec
-```
+### Conda environment
 
-## Steps for developers:
-If you want to work for some developments based on GANrec, please follow the steps below to install and set up GANrec:
-
-
-### 1. Create & Activate a Conda Environment
+#### 1. Create & Activate a Conda Environment
 Open your terminal or command prompt and create a new conda environment named `ganrec` with Python 3.11:
 
 ```bash
 conda create --name ganrec python=3.11
 conda activate ganrec
 ```
-
-### 2. Install Tensorflow OR PyTorch 
-Choose and install either TensorFlow or PyTorch based on your preference.
 
-For TensorFlow:
-```bash
-pip install tensorflow
-```
+#### 2. Install ganrec with your preferred backend (recommended)
+Use pip extras to install GANrec and the backend in one step:
 
-For PyTorch (make sure to select the correct version for your system from the PyTorch website):
 ```bash
-# Example command for installing PyTorch with CUDA support
-pip install torch torchvision torchaudio
-```
-### 3. Clone the GANrec Repository:
-Clone the GANrec repository from GitHub to your local machine.
-```bash  
-git clone https://github.com/XYangXRay/ganrec.git`
+# TensorFlow backend
+pip install "ganrec[tensorflow]"
+
+# PyTorch backend
+pip install "ganrec[pytorch]"
 ```
 
-### 4. Install the Required Packages:
+Notes:
+- For TensorFlow GPU wheels, see TensorFlow’s docs (e.g., tensorflow[and-cuda]) and ensure compatible NVIDIA drivers/CUDA.
+- For PyTorch, use the selector on pytorch.org for OS/CUDA-specific commands if the generic wheel doesn’t match your system.
 
-Navigate to the main directory of the cloned repository and install the necessary packages.
-```bash
-cd ganrec
-python3 -m pip install -e .
-```
 
 ## Additional Notes for Users
 
@@ -120,16 +85,29 @@ PyTorch is favored for its ease of use, dynamic computation graph, and strong su
 ### Installing GPU Support
 ganrec requires heavy duty work with GPU, make sure to install the GPU versions of TensorFlow or PyTorch. Instructions for this can be found on the respective official websites (TensorFlow and PyTorch).
 
-# Examples
+## Examples
 
-GANrec currently has the applications for tomography reconstructon and in-line phase contrast (holography) phase retrieval:
+GANrec currently has applications for tomography reconstruction and in-line phase contrast (holography) phase retrieval:
 
 1. X-ray tomography reconstruction:
    - [Tomography Example](https://github.com/XYangXRay/ganrec/blob/main/examples/tomography_tf.ipynb)
-2. Holography phase retreival:
+2. Holography phase retrieval:
    - [Phase retrieval Example](https://github.com/XYangXRay/ganrec/blob/main/examples/holography_tf.ipynb)
 
-# References
+You can also run the Python examples directly:
+
+```bash
+# TensorFlow tomography example
+pixi run python examples/tomography_tf.py
+
+# TensorFlow holography example
+pixi run python examples/holography_tf.py
+
+# PyTorch tomography example
+pixi -e pytorch run python examples/tomography_torch.py
+```
+
+## References
 
 If you find GANrec is useful in your work, please consider citing: