https://github.com/ldeecke/gmm-torch

Gaussian mixture models in PyTorch.
https://github.com/ldeecke/gmm-torch

gaussian-mixture-models pytorch

Last synced: 4 months ago
JSON representation

Gaussian mixture models in PyTorch.

• Host: GitHub
• URL: https://github.com/ldeecke/gmm-torch
• Owner: ldeecke
• License: mit
• Created: 2018-06-13T10:26:27.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2023-07-15T15:03:42.000Z (12 months ago)
• Last Synced: 2024-01-16T10:45:34.747Z (5 months ago)
• Topics: gaussian-mixture-models, pytorch
• Language: Python
• Homepage:
• Size: 568 KB
• Stars: 450
• Watchers: 4
• Forks: 88
• Open Issues: 8
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Lists

• awesome-stars - ldeecke/gmm-torch - Gaussian mixture models in PyTorch. (Python)

README

        
This repository contains an implementation of a simple **Gaussian mixture model** (GMM) fitted with Expectation-Maximization in [pytorch](http://www.pytorch.org). The interface closely follows that of [sklearn](http://scikit-learn.org).

![Example of a fit via a Gaussian Mixture model.](example.png)

---

A new model is instantiated by calling `gmm.GaussianMixture(..)` and providing as arguments the number of components, as well as the tensor dimension. Note that once instantiated, the model expects tensors in a flattened shape `(n, d)`.

The first step would usually be to fit the model via `model.fit(data)`, then predict with `model.predict(data)`. To reproduce the above figure, just run the provided `example.py`.

Some sanity checks can be executed by calling `python test.py`. To fit data on GPUs, ensure that you first call `model.cuda()`.