deepdow.layers.transform module¶
Collection of layers focusing on transforming tensors while keeping the number of dimensions constant.
-
class
Conv(n_input_channels, n_output_channels, kernel_size=3, method='2D')[source]¶ Bases:
torch.nn.modules.module.ModuleConvolutional layer.
- Parameters
n_input_channels (int) – Number of input channels.
n_output_channels (int) – Number of output channels.
kernel_size (int) – Size of the kernel.
method (str, {'2D, '1D'}) – What type of convolution is used in the background.
-
forward(x)[source]¶ Perform forward pass.
- Parameters
x (torch.Tensor) – Tensor of shape (n_samples, n_input_channels, lookback, n_assets) if `self.method=’2D’. Otherwise (n_samples, n_input_channels, lookback).
- Returns
Tensor of shape (n_samples, n_output_channels, lookback, n_assets) if self.method=’2D’. Otherwise (n_samples, n_output_channels, lookback).
- Return type
torch.Tensor
-
class
RNN(n_channels, hidden_size, cell_type='LSTM', bidirectional=True, n_layers=1)[source]¶ Bases:
torch.nn.modules.module.ModuleRecurrent neural network layer.
- Parameters
n_channels (int) – Number of input channels.
hidden_size (int) – Hidden state size. Alternatively one can see it as number of output channels.
cell_type (str, {'LSTM', 'RNN'}) – Type of the recurrent cell.
bidirectional (bool) – If True, then bidirectional. Note that hidden_size already takes this parameter into account.
n_layers (int) – Number of stacked layers.