ssc4onnx

What it is and what it does

ssc4onnx is a command-line and Python library tool for inspecting the structure of ONNX neural network models. It addresses a specific gap: when models are too large or complex for visual inspection tools like Netron, ssc4onnx provides a text-based breakdown of the model's operations and total byte size. The tool works both as a CLI utility (via `ssc4onnx -if model.onnx`) and as a Python function that accepts either a file path or an in-memory ONNX ModelProto object.

The package has no runtime dependencies beyond Python itself, making installation straightforward. It returns operation counts by type and the model's byte size, useful for understanding model complexity and identifying bottlenecks before deployment. The codebase is part of a larger ONNX processing toolkit maintained on GitHub, though the package itself has not been updated in over 1055 days.

Use it for:

• Inspect the operation breakdown of large ONNX models that cannot be visualized with Netron.
• Verify model structure and operation counts programmatically before deploying to inference engines.
• Analyze model size and complexity as part of model optimization workflows.
• Debug ONNX graph structure issues by examining operation types and counts in text form.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Analyzes and displays the structure of ONNX models, including those too large for graphical tools like Netron, reporting operation counts and model size.

Yes, if you need to inspect large ONNX models and Netron is insufficient. The low install friction and permissive license make it a low-risk addition. However, dormant maintenance (last update over 1055 days ago) means you should verify compatibility with your ONNX opset version before relying on it in production pipelines.

Install

ssc4onnx on PyPI

pip install ssc4onnx

uv add ssc4onnx

poetry add ssc4onnx

Installing ssc4onnx

Before you install

Low install friction; pure Python wheel with no runtime dependencies. Maintenance is dormant—last release was over 1055 days ago, though the repository remains active and unarchived.

License in practice

MIT License permits commercial and private use with minimal restrictions, making it safe to adopt in most projects.

Quickstart

pip install ssc4onnx

from ssc4onnx import structure_check
op_num, model_size = structure_check(
    input_onnx_file_path="model.onnx"
)

Requires Python 3.6 or later; ONNX file must be a valid ONNX model.

Verify before relying

• Whether the package works correctly with recent ONNX opset versions given the dormant maintenance status.
• Performance characteristics when analyzing very large models (exact size thresholds not specified).

Package facts

Evidence: ssc4onnx-1.0.8-py3-none-any.whl

Tags

More Artificial Intelligence packages