LocalConv2d#

class LocalConv2d(in_channels, out_channels, input_height, input_width, kernel_size, stride=1, padding=0, dilation=1, groups=1, conv_mode='cross_correlation', **kwargs)[source]#

Applies a spatial convolution with untied kernels over an groupped channeled input 4D tensor. It is also known as the locally connected layer.

Parameters:

  • in_channels (int) – number of input channels.

  • out_channels (int) – number of output channels.

  • input_height (int) – the height of the input images.

  • input_width (int) – the width of the input images.

  • kernel_size (Union[int, Tuple[int, int]]) – size of weight on spatial dimensions. If kernel_size is an int, the actual kernel size would be (kernel_size, kernel_size).

  • stride (Union[int, Tuple[int, int]]) – stride of the 2D convolution operation. Default: 1

  • padding (Union[int, Tuple[int, int]]) – size of the paddings added to the input on both sides of its spatial dimensions. Only zero-padding is supported. Default: 0

  • dilation (Union[int, Tuple[int, int]]) – dilation of the 2D convolution operation. Default: 1

  • groups (int) – number of groups into which the input and output channels are divided, so as to perform a “grouped convolution”. When groups is not 1, in_channels and out_channels must be divisible by groups. Default: 1

Note

  • weight usually has shape (out_height, out_width, in_channels, height, width, in_channels) , if groups is not 1, shape will be (groups, out_height, out_width, in_channels // groups, height, width, out_channels // groups)

  • bias usually has shape (1, out_channels, *1)