torchflows and normalizing-flows

These tools are competitors, as one provides modern normalizing flows in PyTorch and the other implements normalizing flows in TensorFlow 2, forcing users to choose one framework over the other for their flow implementations.

torchflows
51
Established
normalizing-flows
49
Emerging
Maintenance 10/25
Adoption 5/25
Maturity 25/25
Community 11/25
Maintenance 2/25
Adoption 10/25
Maturity 16/25
Community 21/25
Stars: 12
Forks: 2
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 148
Forks: 36
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: GPL-3.0
No risk flags
Stale 6m No Package No Dependents

About torchflows

davidnabergoj/torchflows

Modern normalizing flows in Python. Simple to use and easily extensible.

This library helps machine learning researchers and practitioners train generative models and estimate data density using modern normalizing flows. You provide your dataset, and it outputs a model that can generate new, similar data points or calculate the likelihood of existing ones. It's designed for those working with advanced machine learning models who need flexible tools for generative tasks.

generative-modeling density-estimation machine-learning-research data-synthesis deep-learning-engineering

About normalizing-flows

LukasRinder/normalizing-flows

Implementation of normalizing flows in TensorFlow 2 including a small tutorial.

This project offers tools to build advanced AI models that can accurately estimate the probability distribution of complex data or generate new, realistic data samples from scratch. You can input various datasets, like sensor readings, financial time series, or images, and output either a detailed understanding of the data's underlying patterns or entirely new data that mimics the original. This is ideal for machine learning researchers, data scientists, and AI developers working on generative models or anomaly detection.

generative-modeling density-estimation deep-learning data-synthesis unsupervised-learning

Scores updated daily from GitHub, PyPI, and npm data. How scores work