A PyTorch-based toolkit for (anatomical) landmark detection in images.
Project description
Landmarker is a PyTorch-based toolkit for (anatomical) landmark detection in images. It is designed to be easy to use and to provide a flexible framework for state-of-the-art landmark detection algorithms for small and large datasets. Landmarker was developed for landmark detection in medical images. However, it can be used for any type of landmark detection problem.
🛠️ Installation
command | |
---|---|
pip | pip install landmarker |
🚀 Getting Started
Technical documentation is available at documentation.
Examples and tutorials are available at examples
✨ Features
- Modular: Landmarker is designed to be modular. It is easy to add new models, datasets, and loss functions.
- Flexible: Landmarker provides a flexible framework for landmark detection. It is easy to customize the training and evaluation process.
- Easy to use: Landmarker is easy to use. It provides a simple API for training and evaluation.
- State-of-the-art: Landmarker provides state-of-the-art landmark detection models and loss functions.
📈 Future Work
- Extension to 3D landmark detection.
- Extension to landmark detection in videos.
- Add uncertainty estimation.
- ...
👪 Contributing
We welcome contributions to Landmarker. Please read the contributing guidelines for more information.
📖 Citation
If you use Landmarker in your research, please cite the following paper:
SCIENTIFIC PAPER UNDER REVIEW
📝 License
Landmark is licensed under the IMEC license.
👤 Jef Jonkers
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for landmarker-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 801d0fb7d5c4bb658cbe7d341b020b8a7eccb17af12333fc785ab49a357a1378 |
|
MD5 | 8d8cb3f6b578de6b18305621acf23f99 |
|
BLAKE2b-256 | eb8681803e0e027d704bfc4f7d37ba55edb6677d86f53eb1dbca5009013d5cc7 |