https://github.com/dfdazac/wassdistance
Approximating Wasserstein distances with PyTorch
https://github.com/dfdazac/wassdistance
deep-learning machine-learning optimal-transport pytorch
Last synced: 6 months ago
JSON representation
Approximating Wasserstein distances with PyTorch
- Host: GitHub
- URL: https://github.com/dfdazac/wassdistance
- Owner: dfdazac
- License: mit
- Created: 2019-02-26T11:32:58.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2023-04-15T10:10:02.000Z (over 2 years ago)
- Last Synced: 2024-08-03T15:06:52.164Z (about 1 year ago)
- Topics: deep-learning, machine-learning, optimal-transport, pytorch
- Language: Jupyter Notebook
- Size: 381 KB
- Stars: 452
- Watchers: 4
- Forks: 56
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Approximating Wasserstein distances with PyTorch
Repository for the blog post on [Wasserstein distances](https://dfdazac.github.io/sinkhorn.html).
***Update (July, 2019):*** I'm glad to see many people have found this post useful. Its main purpose is to introduce and illustrate the problem. To apply these ideas to large datasets and train on GPU, I highly recommend the GeomLoss library, which is optimized for this.
**Instructions**
Create a conda environment with all the requirements (edit `environment.yml` if you want to change the name of the environment):
```sh
conda env create -f environment.yml
```
Activate the environment
```sh
source activate pytorch
```
Open the notebook to reproduce the results:
```sh
jupyter notebook
```