VGGBlock

class eyefeatures.deep.models.VGGBlock(in_channels, out_channels, kernel_size=3, padding=1, stride=1)[source]

Bases: Module

A VGG-style convolutional block consisting of a convolution layer, batch normalization, and ReLU activation.

Parameters:

  • in_channels (int) – (int) Number of input channels.

  • out_channels (int) – (int) Number of output channels.

  • kernel_size (int) – (int, optional) Size of the convolution kernel. Default is 3.

  • padding (int) – (int, optional) Padding for the convolution layer. Default is 1.

  • stride (int) – (int, optional) Stride for the convolution layer. Default is 1.

Returns:

Output tensor after applying the convolution, batch normalization, and

ReLU activation.