# ZhangGe6/onnx-modifier

A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.

Repository: https://github.com/ZhangGe6/onnx-modifier
Canonical: https://ross.abutalabs.com/products/onnx-modifier
Language: JavaScript
License: MIT
License Family: permissive
Topics: editor, onnx, edit, visualize, visualization
Last push: 2026-06-27T15:03:30+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 89, release rhythm 35, longevity 100
- inputs: {"age_days": 1588, "days_push": 67, "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 1627, forks 200 (observed 2026-08-28T04:05:13.116027+00:00)

## What it is
onnx-modifier is a web-based visual editor for ONNX neural network models, built on Netron for graph visualization and Flask as the backend. It lets users delete or add nodes, rename inputs/outputs, edit attributes and initializers, and export the modified model without writing code.

## Use cases
- edit onnx model graph visually
- delete nodes from an onnx model
- rename onnx model inputs and outputs
- change input shape of an onnx model
- edit node attributes in an onnx model
- add new nodes to an onnx model
- modify onnx model initializers without coding

## When to choose
- you need to tweak an ONNX model graph and prefer a GUI over writing ONNX Python API scripts
- you want to preview edits on the model graph interactively before exporting
- you need common operations like renaming tensors, editing shapes, or pruning nodes quickly

## When to avoid
- you need fully scripted or automated batch model transformations
- you work with model formats other than ONNX
- you need a headless or CI-integrated editing pipeline

## Facets
- artifact type: application
- maturity: active
- function: editor, gui, data-visualization, machine-learning, developer-tools
- domain: machine-learning, developer-tools, deep-learning
- platform: cross-platform, python
- tags: onnx, model-editing, netron, flask, model-graph, web-app, web-server, docker

## Member repositories
- ZhangGe6/onnx-modifier (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:13.116027+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 2026-08-30T03:48:23.282637+00:00, confidence not recorded.
  - readme: https://github.com/ZhangGe6/onnx-modifier (fetched 2026-08-28T04:05:13.116027+00:00, sha f80cab336d9c)
- Data as of 2026-08-30T08:39:29.467469+00:00.