Simply open the jupyter notebook and see how some demo on pictures that we uploaded with this repository
What things you need to install the software and how to install them
scikit-image
matplotlib
numpy
pytorch
notebook
scipy
Here are the steps to follow
conda install environment.yml
conda activate lddmm
Simply run main.py
python3 main.py
Our tests are working on anchors example. Here are some examples of results and their explanation.
- Active landmark annotating
- momentum of 0
- two steps gradient descent momentum and control points
- loss: MSE
- regularization: euclidian norm on momentum (integrated on path)
- (optional: affine transform beforehand)
Original images, superposed
Registered images, superposed
Deformation map
None yet, you can do some pull requests to me
- python3 - The web framework used
Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.
Michael Chan
This project is licensed under the MIT License - see the LICENSE.md file for details
...