A pytorch implementation of the most commonly used normalising flows.
-
Updated
Jun 29, 2020 - Python
A pytorch implementation of the most commonly used normalising flows.
This repository contains the code and resources related to the research paper titled "TreeFlow: Going Beyond Tree-based Parametric Probabilistic Regression" by Patryk Wielopolski and Maciej Zięba. The paper is published in 26th European Conference on Artificial Intelligence ECAI 2023.
My solution to the NeurIPS challenge Learn to Move: Walk Around
Framework for analysis of Normalizing Flows based Generative models. Analyses include: similarity between classes, dimensionality reduction (PCA, UMAP), experimental image compression.
Flow-based PC algorithm for causal discovery using Normalizing Flows
Code for reproducing results in my bachelor thesis "Predicting Human Similarity Judgments Using Normalizing Flows"
One-class learning project for anomaly detection using real industrial dataset
Using ML to Simulate Distributions of Observables at the LHC
Solving multiphysics-based inverse problems with learned surrogates and constraints
Code for RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior.
PyTorch Lightning Implementation of Diffusion, GAN, VAE, Flow models
Uncertainty quantification and out-of-distribution detection using surjective normalizing flows
Demo PyTorch code for "Variational Inference with Normalizing Flows" (ICML 2015)
Deep Invertible Generalized Linear Model implemented on top of tensorflow_probability
Nomalizing flows for orbita-free DFT
OpenAI Glow implementation for TPU/GPU
An Invertible Neural Network using Variational-Inference to estimate the model uncertainty
A new type of normalising flows that strikes a good balance among expressiveness, fast inversion and exact Jacobian determinant.
practice generative AI with MNIST
Add a description, image, and links to the normalizing-flows topic page so that developers can more easily learn about it.
To associate your repository with the normalizing-flows topic, visit your repo's landing page and select "manage topics."