direct.nn.conv package

Submodules

direct.nn.conv.conv module

class direct.nn.conv.conv.Conv2d(in_channels, out_channels, hidden_channels, n_convs=3, activation=PReLU(num_parameters=1), batchnorm=False)

Bases: Module

Implementation of a simple cascade of 2D convolutions.

If batchnorm is set to True, batch normalization layer is applied after each convolution.

forward(x)

Performs the forward pass of Conv2d.

Parameters:

x: torch.Tensor

Input tensor.

Returns:

out: torch.Tensor

Convoluted output.

Return type:

Tensor

training: bool

Module contents