Skip to content

Formatters & Code

ONNX Model Metadata

Inspect inputs, outputs and ops of any ONNX model.

Runs in your browser

Drop a .onnx file or click to browse

Understanding ONNX

The model format every framework can read.

What's inside an .onnx file, what the metadata reveals, and how the same model shape runs across PyTorch, TensorFlow, and dozens of runtimes.

The neutral middle.

ONNX (Open Neural Network Exchange, 2017) is a Protobuf-encoded graph format for neural networks. The graph is operator-by-operator: Conv, MatMul, ReLU, Softmax. Any framework that exports to ONNX, any runtime that imports it. Trained in PyTorch, deploy via ONNX Runtime, TensorRT, OpenVINO, Core ML, TFLite. The format decouples the training framework from the production runtime.

What the file contains.

A graph definition: nodes (operators), inputs, outputs, intermediate tensors. The weights as initialiser tensors. The opset version (which version of the operator spec). Optional metadata: model name, producer, version, doc string. The file is one .onnx Protobuf, typically tens of megabytes to a few gigabytes depending on the model. Visualisers like Netron render the graph; the metadata-extractor tool surfaces the high-level facts without rendering.

The metadata worth reading.

producer_name + producer_version — what exported it (PyTorch 2.1, tf2onnx 1.15, etc.). opset_import — operator version, which decides what runtime can read it. graph.input — list of input tensors with shapes (often with dynamic batch dimensions). graph.output— output shapes. Total parameter count and approximate FLOPs derived from the graph. Before deploying a third-party model, this metadata is what tells you it'll fit your runtime.

Opset versions matter.

The ONNX spec evolves; opset versions add operators or change behaviour. A model exported with opset 18 won't load on a runtime that only supports up to opset 13 — the runtime doesn't know the new operators. The fix is either upgrading the runtime or re-exporting the model with a lower opset. The exporter's compatibility flag (opset_version=13) is the easy lever; some operators just don't exist in older opsets.

A worked inspection.

Download a third-party detection model: yolov8n.onnx, 12 MB. Metadata inspection: producer ultralytics 8.2, opset 17, input shape [1, 3, 640, 640] (NCHW format), output shape [1, 84, 8400]. ~3 million parameters. The opset tells you ONNX Runtime ≥ 1.14 is required; the input shape tells you images need 640×640 preprocessing in CHW layout; the output shape tells you 8400 anchor boxes, each with 84 features (4 bbox + 80 class scores). Three numbers; whole deployment story.

YOLOv8n.onnx

12 MB, opset 17

Inspect before deploying.

input [1,3,640,640] ; output [1,84,8400]

= ORT ≥ 1.14 needed

Quantisation and pruning.

ONNX supports quantised models: weights stored as int8 instead of float32, 4× smaller and usually faster. Static quantisation needs calibration data; dynamic quantisation needs nothing but trades a bit more accuracy. The metadata tool shows the operator types — Conv vs QLinearConv, MatMul vs MatMulInteger — so you know whether a downloaded model is quantised before you wonder why it's so fast. Pruning shows up as zeroed weights; ONNX doesn't drop them automatically.

Frequently asked questions

Quick answers.

Is my model file uploaded to a server?

No. The inspection logic runs locally in your browser using the File API. Your model data never leaves your device.

What metadata can I see?

You can view the producer name, graph inputs and outputs with their respective shapes, operator sets, and any custom metadata properties stored in the file.

Which ONNX versions are supported?

The tool supports all standard ONNX versions. It reads the `ir_version` and `opset_import` fields to show you which specification the model follows.

Can I see the individual weights or biases?

This tool focuses on structure and metadata rather than tensor data. It lists the names and shapes of initialisers but does not display the raw numerical weights to keep the interface lightweight.

People also search for

Related tools

More in this room.

See all in Formatters & Code