How to adjust a Neural Networks metadata

Metadata of a Neural Network stored in the ONNX file format can be adjusted using the python code found below.

Prerequisites

An installed python environment is required to execute the code. Additionally, install the onnx library using PIP:

pip install onnx 

To add or edit a metadata key (without duplication), you can use the following code:

def addMeta(onnx_model, key, value):
    
    for entry in onnx_model.metadata_props:
        if entry.key == key:
            entry.value = value
            return

    meta = onnx_model.metadata_props.add()
    meta.key = key
    meta.value = value

To adjust an existing ONNX file, you first have to load the model. Next, pass the model to the method, with additional key and value arguments.

import onnx
onnx_model = onnx.load("path/to/onnx/file")
addMeta(onnxModel, "key", "value")

Lastly, save the onnx model again to a (new) file:

with open(onnxFilePath, "wb") as f:
    f.write(onnx_model.SerializeToString())

Producer, version and description are set using these functions, as these are not stored in the meta data.

def setProducer(onnxModel, producer):
    onnxModel.producer_name = producer

def setModelVersion(onnxModel, modelVersion):
    onnxModel.model_version = modelVersion

def setDocString(onnxModel, description):
    onnxModel.doc_string = description

See also

• Neural Network
• ONNX

---

Inference Overlay

Inference Overlay

Tutorials

Overview

Theory

Benchmarks

Group

Model attributes

Inference

Neural Network • Input tensor • Output tensor

Model attributes

Box overlap • Inference mode • Mask threshold • Prioritize labels • Score threshold • Stride fraction

Prequels

A • B

Result types

Boxes • Labels • Masks • Scores • Debug gt instances • Center points

Neural Networks

Foliage • Solar panels