Metadata-Version: 2.4
Name: konfai
Version: 1.2.9
Summary: Modular and configurable Deep Learning framework with YAML and PyTorch
Author-email: Valentin Boussot <boussot.v@gmail.com>
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/vboussot/KonfAI
Project-URL: Repository, https://github.com/vboussot/KonfAI
Project-URL: Issues, https://github.com/vboussot/KonfAI/issues
Project-URL: License, https://www.apache.org/licenses/LICENSE-2.0
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch
Requires-Dist: tqdm
Requires-Dist: numpy
Requires-Dist: ruamel.yaml
Requires-Dist: psutil
Requires-Dist: tensorboard
Requires-Dist: SimpleITK
Requires-Dist: lxml
Requires-Dist: h5py
Requires-Dist: pynvml
Requires-Dist: requests
Provides-Extra: vtk
Requires-Dist: vtk; extra == "vtk"
Provides-Extra: lpips
Requires-Dist: lpips; extra == "lpips"
Provides-Extra: cluster
Requires-Dist: submitit; extra == "cluster"
Dynamic: license-file

[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/vboussot/KonfAI/blob/main/LICENSE)
[![PyPI version](https://img.shields.io/pypi/v/konfai)](https://pypi.org/project/konfai/)

# 🧠 KonfAI
<img src="https://raw.githubusercontent.com/vboussot/KonfAI/main/logo.png" alt="KonfAI Logo" width="250" align="right"/>

**KonfAI** is a modular and highly configurable deep learning framework built on PyTorch, driven entirely by YAML configuration files.

It is designed to support complex medical imaging workflows, flexible model architectures, customizable training loops, and advanced loss scheduling, without hardcoding anything.

---

## 🔧 Key Features

- 🔀 Full training/prediction/evaluation orchestration via YAML configuration file
- 🧩 Modular plugin-like structure (transforms, augmentations, models, losses, schedulers)
- 🔄 Dynamic criterion scheduling per head / target
- 🧠 Multi-branch / multi-output model support
- 🖥️ Cluster-ready
- 📈 TensorBoard and custom logging support

---

## 🚀 Installation

### From PyPI

Install KonfAI from PyPI:

```
pip install konfai
```

This will install the command-line tools:

```
konfai --help
konfai-cluster --help
```

---

### From GitHub

Clone the repository and install:

```
git clone https://github.com/vboussot/KonfAI.git
cd KonfAI
pip install -e .
```

---

## 🧪 Usage

```bash
konfai TRAIN --gpu 0
konfai PREDICTION --gpu 0
konfai EVALUATION
```
