PyTorch Lightning Inference Monitoring
See the Quick Start guide on how to install and configure Graphsignal.
Use a Trainer callback for prediction phases:
from graphsignal.callbacks.pytorch_lightning import GraphsignalCallback
trainer = Trainer(..., callbacks=[GraphsignalCallback()])
trainer.predict()
Note: avoid using other PyTorch Lightning profilers simultaneously.
Examples
The PyTorch Lightning MNIST example illustrates how to add the callback.
Model serving
Graphsignal provides a built-in support for server applications. See Model Serving guide for more information.