Metadata-Version: 2.4
Name: srforge
Version: 0.1.0
Summary: Super‑resolution research framework for PyTorch with a focus on simplicity and flexibility using config files.
Author-email: Tomasz Tarasiewicz <tarasiewicztomasz@gmail.com>
Project-URL: Homepage, https://gitlab.com/tarasiewicztomasz/sr-forge
Project-URL: Source, https://gitlab.com/tarasiewicztomasz/sr-forge/-/tree/main
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: torch>=2.7
Requires-Dist: torchvision>=0.22
Requires-Dist: torchaudio>=2.7
Requires-Dist: torch-geometric>=2.6
Requires-Dist: pyg-lib>=0.4
Requires-Dist: torch-scatter>=2.1
Requires-Dist: torch-sparse>=0.6
Requires-Dist: torch-cluster>=1.6
Requires-Dist: torch-spline-conv>=1.2
Requires-Dist: torchdatasets>=0.2
Requires-Dist: torchmetrics>=1.7
Requires-Dist: hydra-core>=1.3
Requires-Dist: einops>=0.8
Requires-Dist: wandb>=0.21
Requires-Dist: matplotlib>=3.10
Requires-Dist: scikit-image>=0.25
Requires-Dist: opencv-python>=4.12
Requires-Dist: pandas>=2.3
Requires-Dist: colorlog>=6.9
Provides-Extra: cuda128
Requires-Dist: torch==2.7.1+cu128; extra == "cuda128"
Requires-Dist: torchvision==0.22.1+cu128; extra == "cuda128"
Requires-Dist: torchaudio==2.7.1+cu128; extra == "cuda128"
Requires-Dist: torch-geometric==2.6.1; extra == "cuda128"
Requires-Dist: pyg-lib==0.4.0+pt27cu128; extra == "cuda128"
Requires-Dist: torch-scatter==2.1.2+pt27cu128; extra == "cuda128"
Requires-Dist: torch-sparse==0.6.18+pt27cu128; extra == "cuda128"
Requires-Dist: torch-cluster==1.6.3+pt27cu128; extra == "cuda128"
Requires-Dist: torch-spline-conv==1.2.2+pt27cu128; extra == "cuda128"

# SR FORGE
**Super-Resolution Framework for Oriented Restoration and Guided Enhancement**

---

SR FORGE (**S**uper-**R**esolution **F**ramework for **O**riented **R**estoration & **G**uided **E**nhancement) is a unified, modular, and task-driven framework for training and evaluating deep learning models in the field of super-resolution.

## Key Features

- **Structured Workflow**  
  SR FORGE provides an **organized** approach to super resolution. Every step—from data loading to final evaluation—follows a clear, modular structure.

- **Task-driven restoration**  
  Built-in utilities to help fine-tune models for specific tasks or objectives (e.g., OCR, remote sensing, medical imaging, etc.).

- **Config-Driven Experiments**  
  Simple YAML/JSON configuration files let you customize your pipeline without modifying code directly.

- **Flexible Model Plug-In**  
  Easily integrate popular SISR (EDSR, RCAN, ESRGAN, etc.) and MISR (RAMS, HighRes-net, PIUNET, TR-MISR, MagNAt) or your own custom architecture.

- **Unified Metrics**  
  Evaluate your models with a suite of standard metrics (PSNR, SSIM, LPIPS) and straightforward logging.

- **Visualization Tools**  
  Quickly visualize results (side-by-side comparisons, zoom-ins, or overlays) for interpretability and debugging.

## Installation

1. **Clone the Repository**
   ```bash
   git clone https://github.com/your-username/sr-forge.git
