timesead.models.layers.autoformer_encdec
========================================

.. py:module:: timesead.models.layers.autoformer_encdec


Classes
-------

.. autoapisummary::

   timesead.models.layers.autoformer_encdec.CustomLayerNorm
   timesead.models.layers.autoformer_encdec.MovingAvg
   timesead.models.layers.autoformer_encdec.SeriesDecomp
   timesead.models.layers.autoformer_encdec.EncoderLayer
   timesead.models.layers.autoformer_encdec.Encoder


Module Contents
---------------

.. py:class:: CustomLayerNorm(channels)

   Bases: :py:obj:`torch.nn.Module`


   Special designed layernorm for the seasonal part

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


   .. py:attribute:: layernorm


   .. py:method:: forward(x)


.. py:class:: MovingAvg(kernel_size, stride)

   Bases: :py:obj:`torch.nn.Module`


   Moving average block to highlight the trend of time series

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


   .. py:attribute:: kernel_size


   .. py:attribute:: avg


   .. py:method:: forward(x)


.. py:class:: SeriesDecomp(kernel_size)

   Bases: :py:obj:`torch.nn.Module`


   Series decomposition block

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


   .. py:attribute:: moving_avg


   .. py:method:: forward(x)


.. py:class:: EncoderLayer(attention, d_model, d_ff=None, moving_avg=25, dropout=0.1, activation='relu')

   Bases: :py:obj:`torch.nn.Module`


   Autoformer encoder layer with the progressive decomposition architecture

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


   .. py:attribute:: attention


   .. py:attribute:: conv1


   .. py:attribute:: conv2


   .. py:attribute:: decomp1


   .. py:attribute:: decomp2


   .. py:attribute:: dropout


   .. py:attribute:: activation


   .. py:method:: forward(x, attn_mask=None)


.. py:class:: Encoder(attn_layers, conv_layers=None, norm_layer=None)

   Bases: :py:obj:`torch.nn.Module`


   Autoformer encoder

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


   .. py:attribute:: attn_layers


   .. py:attribute:: conv_layers


   .. py:attribute:: norm
      :value: None



   .. py:method:: forward(x, attn_mask=None)