timesead.models.layers.multi_wavelet_correlation

Classes

MultiWaveletTransform	1D multiwavelet block.
MultiWaveletCross	1D Multiwavelet Cross Attention layer.
FourierCrossAttentionW	Base class for all neural network modules.
sparseKernelFT1d	Base class for all neural network modules.
MWT_CZ1d	Base class for all neural network modules.

Functions

legendreDer(k, x)
phi_(phi_c, x[, lb, ub])
get_phi_psi(k, base)
get_filter(base, k)

Module Contents

timesead.models.layers.multi_wavelet_correlation.legendreDer(k, x)

timesead.models.layers.multi_wavelet_correlation.phi_(phi_c, x, lb=0, ub=1)

timesead.models.layers.multi_wavelet_correlation.get_phi_psi(k, base)

timesead.models.layers.multi_wavelet_correlation.get_filter(base, k)

class timesead.models.layers.multi_wavelet_correlation.MultiWaveletTransform(ich=1, k=8, alpha=16, c=128, nCZ=1, L=0, base='legendre', attention_dropout=0.1)

Bases: torch.nn.Module

1D multiwavelet block.

Initialize internal Module state, shared by both nn.Module and ScriptModule.

k = 8

c = 128

L = 0

nCZ = 1

Lk0

Lk1

ich = 1

MWT_CZ

forward(queries, keys, values, attn_mask)

class timesead.models.layers.multi_wavelet_correlation.MultiWaveletCross(in_channels, out_channels, seq_len_q, seq_len_kv, modes, c=64, k=8, ich=512, L=0, base='legendre', mode_select_method='random', initializer=None, activation='tanh', **kwargs)

Bases: torch.nn.Module

1D Multiwavelet Cross Attention layer.

Initialize internal Module state, shared by both nn.Module and ScriptModule.

c = 64

k = 8

L = 0

max_item = 3

attn1

attn2

attn3

attn4

T0

Lk

Lq

Lv

out

modes1

forward(q, k, v, mask=None)

wavelet_transform(x)

evenOdd(x)

class timesead.models.layers.multi_wavelet_correlation.FourierCrossAttentionW(in_channels, out_channels, seq_len_q, seq_len_kv, modes=16, activation='tanh', mode_select_method='random')

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

Initialize internal Module state, shared by both nn.Module and ScriptModule.

in_channels

out_channels

modes1 = 16

activation = 'tanh'

compl_mul1d(order, x, weights)

forward(q, k, v, mask)

class timesead.models.layers.multi_wavelet_correlation.sparseKernelFT1d(k, alpha, c=1, nl=1, initializer=None, **kwargs)

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

Initialize internal Module state, shared by both nn.Module and ScriptModule.

modes1

scale

weights1

weights2

k

compl_mul1d(order, x, weights)

forward(x)

class timesead.models.layers.multi_wavelet_correlation.MWT_CZ1d(k=3, alpha=64, L=0, c=1, base='legendre', initializer=None, **kwargs)

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

Initialize internal Module state, shared by both nn.Module and ScriptModule.

k = 3

L = 0

max_item = 3

A

B

C

T0

forward(x)

wavelet_transform(x)

evenOdd(x)