Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ziatdinovmax/pyroved
Invariant representation learning from imaging and spectral data
https://github.com/ziatdinovmax/pyroved
encoder-decoder-model image-data probabilistic-programming pyro rotation-invariant scale-invariance semi-supervised-learning semi-supervised-vae spectral-data translation-invariant unsupervised-machine-learning vae variational-autoencoder
Last synced: about 2 months ago
JSON representation
Invariant representation learning from imaging and spectral data
- Host: GitHub
- URL: https://github.com/ziatdinovmax/pyroved
- Owner: ziatdinovmax
- License: mit
- Created: 2021-02-25T00:13:07.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2024-01-29T20:33:28.000Z (11 months ago)
- Last Synced: 2024-10-24T16:35:21.581Z (about 2 months ago)
- Topics: encoder-decoder-model, image-data, probabilistic-programming, pyro, rotation-invariant, scale-invariance, semi-supervised-learning, semi-supervised-vae, spectral-data, translation-invariant, unsupervised-machine-learning, vae, variational-autoencoder
- Language: Python
- Homepage:
- Size: 112 MB
- Stars: 48
- Watchers: 3
- Forks: 11
- Open Issues: 8
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# pyroVED
---
[](https://github.com/ziatdinovmax/pyroVED/actions/workflows/actions.yml)
[](https://codecov.io/gh/ziatdinovmax/pyroVED)
[](https://pyroved.readthedocs.io/en/latest/README.html)
[](https://badge.fury.io/py/pyroved)
pyroVED is an open-source package built on top of the Pyro probabilistic programming framework for applications of variational encoder-decoder models in spectral and image analyses. The currently available models include variational autoencoders with translational, rotational, and scale invariances for unsupervised, class-conditioned, and semi-supervised learning, as well as *im2spec*-type models for predicting spectra from images and vice versa.
More models to come!
## Documentation and Examples
The documentation of the package content can be found [here](https://pyroved.readthedocs.io/).
The easiest way to start using pyroVED is via [Google Colab](https://colab.research.google.com/notebooks/intro.ipynb), which is a free research tool from Google for machine learning education and research built on top of Jupyter Notebook. The following notebooks can be executed in Google Colab by simply clicking on the "Open in Colab" icon:
* Mastering the 1D shifts in spectral data [](https://colab.research.google.com/github/ziatdinovmax/pyroVED/blob/master/examples/shiftVAE.ipynb)
* Disentangling image content from rotations [](https://colab.research.google.com/github/ziatdinovmax/pyroVED/blob/master/examples/rVAE.ipynb)
* Learning (jointly) discrete and continuous representations of data [](https://colab.research.google.com/github/ziatdinovmax/pyroVED/blob/main/examples/jrVAE.ipynb)
* Semi-supervised learning from data with orientational disorder [](https://colab.research.google.com/github/ziatdinovmax/pyroVED/blob/main/examples/ssrVAE.ipynb)
* im2spec: Predicting 1D spectra from 2D images [](https://colab.research.google.com/github/ziatdinovmax/pyroVED/blob/main/examples/im2spec_VED.ipynb)
## Installation
#### Requirements
* python >= 3.6
* [pytorch](https://pytorch.org/) >= 1.8
* [pyro-ppl](https://pyro.ai/) >= 1.6
Install pyroVED using pip:
```bash
pip install pyroved
```
#### Latest (unstable) version
To upgrade to the latest (unstable) version, run
```bash
pip install --upgrade git+https://github.com/ziatdinovmax/pyroved.git
```
## Reporting bugs
If you found a bug in the code or would like a specific feature to be added, please create a report/request [here](https://github.com/ziatdinovmax/pyroVED/issues/new/choose).
## Development
To run the unit tests, you'll need to have a pytest framework installed:
```bash
python3 -m pip install pytest
```
Then run tests as:
```bash
pytest tests
```
If this is your first time contributing to an open-source project, we highly recommend starting by familiarizing yourself with these very nice and detailed contribution [guidelines](https://github.com/firstcontributions/first-contributions).