conv {cito}

Convolutional layer

Description

creates a 'conv' 'citolayer' object that is used by create_architecture.

Usage

conv(
  n_kernels = NULL,
  kernel_size = NULL,
  stride = NULL,
  padding = NULL,
  dilation = NULL,
  bias = NULL,
  activation = NULL,
  normalization = NULL,
  dropout = NULL
)

Arguments

n_kernels

(int) amount of kernels in this layer

kernel_size

(int or tuple) size of the kernels in this layer. Use a tuple if the kernel size isn't equal in all dimensions

stride

(int or tuple) stride of the kernels in this layer. NULL sets the stride equal to the kernel size. Use a tuple if the stride isn't equal in all dimensions

padding

(int or tuple) zero-padding added to both sides of the input. Use a tuple if the padding isn't equal in all dimensions

dilation

(int or tuple) dilation of the kernels in this layer. Use a tuple if the dilation isn't equal in all dimensions

bias

(boolean) if TRUE, adds a learnable bias to the kernels of this layer

activation

(string) activation function that is used after this layer. The following activation functions are supported: "relu", "leaky_relu", "tanh", "elu", "rrelu", "prelu", "softplus", "celu", "selu", "gelu", "relu6", "sigmoid", "softsign", "hardtanh", "tanhshrink", "softshrink", "hardshrink", "log_sigmoid"

normalization

(boolean) if TRUE, batch normalization is used after this layer

dropout

(float) dropout rate of this layer. Set to 0 for no dropout

Details

This function creates a 'conv' 'citolayer' object that is passed to the create_architecture function. The parameters that aren't assigned here (and are therefore still NULL) are filled with the default values passed to create_architecture.

Value

S3 object of class "conv" "citolayer"

Author(s)

Armin Schenk

See Also

create_architecture