neuralop.layers.spectral_convolution.SpectralConv3d

class neuralop.layers.spectral_convolution.SpectralConv3d(in_channels, out_channels, n_modes, max_n_modes=None, bias=True, n_layers=1, separable=False, output_scaling_factor: int | float | List[float | int] | None = None, fno_block_precision='full', rank=0.5, factorization=None, implementation='reconstructed', fixed_rank_modes=False, joint_factorization=False, decomposition_kwargs: dict | None = None, init_std='auto', fft_norm='backward', device=None, dtype=None)[source]

3D Spectral Conv, see neuralop.layers.SpectraConv for the general case

This is provided for reference only, see neuralop.layers.SpectraConv for the preferred, general implementation

Methods

forward(x[, indices])

Generic forward pass for the Factorized Spectral Conv

forward(x, indices=0)[source]

Generic forward pass for the Factorized Spectral Conv

Parameters:

xtorch.Tensor

input activation of size (batch_size, channels, d1, …, dN)

indicesint, default is 0

if joint_factorization, index of the layers for n_layers > 1

Returns:

tensorized_spectral_conv(x)