Conv2dReLU¶

class Conv2dReLU(in_channels, out_channels, kernel_size, padding=0, stride=1, *, bias=False, batch_norm_eps=1e-05, batch_norm_momentum=0.1)[source]¶

Conv2d + BatchNorm + ReLU block.

Initialize Conv2dReLU block.

Parameters:

  • in_channels (int) – Number of input channels.

  • out_channels (int) – Number of output channels.

  • kernel_size (int) – Convolution kernel size.

  • padding (int) – Padding applied to the input.

  • stride (int) – Convolution stride.

  • bias (bool) – If True, adds a learnable bias to the convolution output.

  • batch_norm_eps (float) – Epsilon value for batch normalization.

  • batch_norm_momentum (float) – Momentum value for batch normalization.

Methods

Attributes

training