# lutzroeder/netron

Visualizer for neural network, deep learning and machine learning models

Repository: https://github.com/lutzroeder/netron
Canonical: https://ross.abutalabs.com/products/netron
Homepage: https://netron.app
Language: JavaScript
License: MIT
License Family: permissive
Topics: neural-network, deep-learning, machine-learning, deeplearning, machinelearning, ai, ml, visualizer, onnx, keras, tensorflow, tensorflow-lite, coreml, pytorch, numpy, safetensors
Last push: 2026-08-26T15:45:52+00:00

## Health v2 (maintenance only)
Score: 99/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 100
- inputs: {"age_days": 5729, "days_push": 7, "days_rel": 19, "gap_med": 7.0, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 33407, forks 3178 (observed 2026-08-28T04:11:58.304596+00:00)

## What it is
Netron is a visualizer for neural network, deep learning, and machine learning models, rendering model graphs and layer details. It supports ONNX, TensorFlow Lite, PyTorch, TensorFlow, Core ML, Keras, and many other formats, available as a desktop app, browser app, or Python package.

## Use cases
- visualize onnx model graph
- inspect tensorflow lite model layers
- view pytorch model architecture
- open coreml model in a viewer
- debug neural network model structure
- explore keras model topology

## When to choose
- you need to inspect or debug a model's graph, weights, or metadata across many ML formats
- you want a quick no-install way to view models via the browser version

## When to avoid
- you need to train or run inference on models rather than visualize them
- you need programmatic graph manipulation rather than visual inspection

## Facets
- artifact type: application
- maturity: active
- function: data-visualization, machine-learning, developer-tools
- domain: machine-learning, deep-learning, developer-tools, data-visualization
- platform: cross-platform, windows, browser, python
- tags: model-viewer, onnx, tensorflow, pytorch, neural-network-visualization, model-inspection, macos, linux

## Member repositories
- lutzroeder/netron (main) score 99

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:58.304596+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 2026-08-29T16:28:19.148741+00:00, confidence not recorded.
  - readme: https://github.com/lutzroeder/netron (fetched 2026-08-28T04:11:58.304596+00:00, sha 5fc20536c76a)
  - homepage: https://netron.app (fetched 2026-08-29T07:48:50.399148+00:00, sha 763bc3574555)
- Data as of 2026-08-30T08:39:29.467469+00:00.