ONNX Runtime Monitoring

See the Quick Start guide on how to install and configure Graphsignal.

Add the following code before inference session initialization and around inference. See API reference for full documentation.

import onnxruntime

session = onnxruntime.InferenceSession('my-model-path')

with graphsignal.start_trace(endpoint='predict'):
    session.run(...)

Examples

The ONNX MNIST example illustrates how to add and configure ONNX Runtime measurement and recording.

Model serving

Graphsignal provides a built-in support for server applications. See Model Serving guide for more information.