Self-supervised¶
This guide shows how to train a neural operator on sine functions
in a self-supervised manner using the SelfSupervisedOperatorDataset
.
Setup¶
Dataset¶
Create a data set of sine waves: The SineBenchmark
generates SelfSupervisedDataset
that exports samples
for self-supervised training, namely
This dataset contains 128 samples. Let's plot a random one!
Operator¶
In this example, we use a NaiveIntegralKernel
as neural operator with a
NeuralNetworkKernel
as kernel function.
Training¶
Train the neural operator.
Plotting¶
Plot model predictions for training data.
Generalization¶
Plot prediction on a test sample which was not part of the training set.
Last update:
2024-08-20
Created: 2024-08-20
Created: 2024-08-20