unet: U-Net Block

In neuroimaginador/dl4ni: Deep Learning Flows for Neuroimaging

Description

This function is a wrapper to define a U-Net convolutional block.

Usage

unet(initial_filters = 2, depth = 3, ...)

Arguments

initial_filters	(integer) Number of initial filters used in the first layer, Default: 2
depth	(integer) Steps for the downsampling path, Default: 3
...	arguments for the block_downsample function.
kernel_size	(list or vector) size of the kernels to use, Default: c(3, 3, 3)

Value

A list with type = "unet" and params with the rest of parameters that define the block.

neuroimaginador/dl4ni documentation built on May 3, 2019, 5:47 p.m.