https://github.com/siboehm/normalizingflownetwork
Bayesian and Maximum Likelihood Implementation of the Normalizing Flow Network (NFN): https://arxiv.org/abs/1907.08982
https://github.com/siboehm/normalizingflownetwork
conditional-density-estimation normalizing-flows
Last synced: about 1 month ago
JSON representation
Bayesian and Maximum Likelihood Implementation of the Normalizing Flow Network (NFN): https://arxiv.org/abs/1907.08982
- Host: GitHub
- URL: https://github.com/siboehm/normalizingflownetwork
- Owner: siboehm
- Created: 2019-05-22T09:45:05.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2020-12-10T09:09:16.000Z (over 4 years ago)
- Last Synced: 2025-04-18T08:40:06.887Z (about 1 month ago)
- Topics: conditional-density-estimation, normalizing-flows
- Language: Python
- Homepage: https://arxiv.org/abs/1907.08982
- Size: 174 KB
- Stars: 21
- Watchers: 5
- Forks: 8
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# (Bayesian) Normalizing Flow Network
A Normalizing Flow based model for Conditional Density Estimation.
More info about the NFN: [paper](https://arxiv.org/abs/1907.08982), [blog post](https://siboehm.com/articles/19/normalizing-flow-network)
## This repo implements:
### Conditional Density Estimators:
- Normalizing Flow Network (NFN)
- Mixture Density Network (MDN)
- Kernel Mixture Network (KMN)
### Normalizing Flows
- Radial Flow
- Planar Flow
- Affine Flow
## Installing dependencies
Tested with Python version 3.8.
```bash
pip install -r requirements.txt
pip install -e .
# Only necessary for running the evaluation scripts, not necessary for development
pip install --no-dependencies cde
```
## Running tests
Tests are implemented using pytest
```bash
# run full test suit
pytest tests/
# run tests without the slow integration tests
pytest tests/ -m "not slow"
```