I'm using Pytorch-Geometric to create a GNN and I'd like to be able to run it inside an application that supports ONNX inference, but I can't seem to find any information on how or whether this is possible. How do I export a PyG GNN model and how can I run inference on it?
Ask a Question
Question
I'm using Pytorch-Geometric to create a GNN and I'd like to be able to run it inside an application that supports ONNX inference, but I can't seem to find any information on how or whether this is possible. How do I export a PyG GNN model and how can I run inference on it?