What version of Fourier Neural Operator is used in the MWT paper?

[scaomath]

Hi, thanks for the sharing the nicely written code on the wavelet neural operator.

I wonder what version of FNO is used in the comparison? for example in Table 2 of https://arxiv.org/abs/2109.13459v1

Because in Table 2, FNO1d still has only 1e-2 evaluation relative error for the Burgers' benchmark.

In the new implementation, if BatchNorm is removed, and change the ReLU activation to GeLU or SiLU, 500 epochs of MultiStepLR scheduling will yield about 2.5e-3 to 2.7e-3 evaluation relative error: see neuraloperator/neuraloperator#30 , even with a 1cycleLR + 100 epochs, the evaluation error is around 4.1e-3.

[gaurav71531]

For Burgers' eqn the results are in Table-7 where after using 3 seeds we get average error ~3.33e-3. We have used Pytorch 1.8 cu 11.0

[scaomath]

Thanks.