How to save the trained model and use for final test like demo?

[DL8614]

Hi,
I am training the model with my own dataset and I am saving the model with
torch.save(classifier.state_dict(), PATH)

However, when I load it, it shows IncompatibleKeys(missing_keys=[], unexpected_keys=[])
It looks that, it saves nothing? How can I save it?

One other question is that. if validation loss looks very low. Then how can I use that trained model with some unknown graph for graph class prediction?

[muhanzhang]

It looks like it is saving the model, with no keys missing or unexpected. Maybe this post helps you?

For your second question, do you mean validation accuracy (instead of loss) very low? If so, it is better to tune the architecture/hyperparameters to make it high before applying to unknown graphs.