# sksq96/pytorch-summary

Model summary in PyTorch similar to `model.summary()` in Keras

Repository: https://github.com/sksq96/pytorch-summary
Canonical: https://ross.abutalabs.com/products/pytorch-summary
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, keras, summary, deep-learning
Last push: 2024-03-02T15:10:25+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3054, "days_push": 914, "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 4053, forks 409 (observed 2026-08-28T04:08:33.869387+00:00)

## What it is
A PyTorch library providing a Keras-style model.summary() that prints layer types, output shapes, parameter counts, and memory estimates. It is now superseded by the maintained torchinfo package.

## Use cases
- print a keras-style summary of a pytorch model
- count trainable parameters in a pytorch network
- show layer output shapes for debugging a cnn
- estimate model memory footprint in pytorch
- inspect pytorch model architecture like keras model.summary()

## When to avoid
- you are starting a new project - use torchinfo instead
- you need summaries of models with multiple inputs or complex control flow

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, developer-tools
- domain: deep-learning, machine-learning, developer-tools
- platform: python
- tags: pytorch, model-summary, keras-style, debugging, neural-networks

## Member repositories
- sksq96/pytorch-summary (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:33.869387+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 2026-08-29T18:23:39.012303+00:00, confidence not recorded.
  - readme: https://github.com/sksq96/pytorch-summary (fetched 2026-08-28T04:08:33.869387+00:00, sha 3100f04c1e6e)
- Data as of 2026-08-30T08:39:29.467469+00:00.