jmschrei/pomegranate

Health v2 · maintenance only

Adoption not part of the score

3542 stars · 599 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Pomegranate is a Python library for fast and flexible probabilistic modeling, built on PyTorch. It supports distributions, mixture models, Bayesian networks, and hidden Markov models that compose modularly with GPU acceleration.

Use cases

• fit a gaussian mixture model in python
• train a hidden markov model for sequences
• build a bayesian network from data
• probabilistic modeling with gpu acceleration
• create a mixture of gamma and poisson distributions
• classify sequences with hmm-based classifiers

When to choose

• you need composable probabilistic models like mixtures, Bayesian networks, or HMMs
• you want PyTorch-backed speed, GPU support, and mixed precision
• you want models treated as probability distributions that nest inside each other

When to avoid

• you rely on the pre-1.0 Cython API, which is incompatible
• you only need general deep learning without probabilistic modeling
• you need a non-Python environment

Facets

library · maturity active

machine-learning math machine-learning data-science python cross-platform probabilistic-modeling pytorch bayesian-networks hidden-markov-models mixture-models probability-distributions algorithms gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jmschrei/pomegranate")