ResnetBlock

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

Bases: Module

A ResNet-style residual block consisting of two convolution layers

with skip connections.

Parameters:

  • in_channels (int) – Number of input channels.

  • out_channels (int) – Number of output channels.

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

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

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

Returns:

Output tensor after applying residual connection and ReLU activation.