# jmtomczak/intro_dgm

"Deep Generative Modeling": Introductory Examples

Repository: https://github.com/jmtomczak/intro_dgm
Canonical: https://ross.abutalabs.com/products/intro_dgm
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: deep-generative-modelling, variational-autoencoder, flow-based-modeling, autoregressive-modeling, pytorch, generative-adversarial-network, energy-based-model, neural-compression, deep-learning, generative-ai, score-based-generative-modeling
Last push: 2026-04-28T23:22:38+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 79, release rhythm 35, longevity 100
- inputs: {"age_days": 2048, "days_push": 127, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1336, forks 205 (observed 2026-08-28T04:04:25.551819+00:00)

## What it is
A companion repository of introductory Jupyter Notebook examples for the book 'Deep Generative Modeling' by Jakub Tomczak. It provides simple, runnable PyTorch implementations of major deep generative model classes such as autoregressive models, flows, VAEs, GANs, energy-based, and score-based models.

## Use cases
- learn how variational autoencoders work with runnable code
- understand flow-based and autoregressive generative models
- get simple PyTorch examples of GANs and energy-based models
- study score-based generative modeling basics
- follow along with a deep generative modeling textbook
- run quick generative model experiments on a laptop

## When to choose
- you are learning deep generative models from scratch
- you want minimal, readable PyTorch implementations to study line by line
- you are reading the 'Deep Generative Modeling' book and want its code examples
- you need lightweight examples that run on a laptop without GPUs

## When to avoid
- you need production-ready or state-of-the-art generative model implementations
- you want a full training framework with advanced features and scaling
- you need large-scale image or text generation systems

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning, tutorials
- platform: python
- tags: generative-models, variational-autoencoder, gan, flow-based-models, energy-based-models, score-based-models, pytorch, jupyter-notebooks, neural-compression, book-companion

## Member repositories
- jmtomczak/intro_dgm (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:25.551819+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:44:15.678715+00:00, confidence not recorded.
  - readme: https://github.com/jmtomczak/intro_dgm (fetched 2026-08-28T04:04:25.551819+00:00, sha 86408811c050)
- Data as of 2026-08-30T08:39:29.467469+00:00.