Description Usage Arguments Details Value See Also
This function creates a block of convolutional layers with max pooling such that the dimension of the outputs is halved after each block.
1 2 3 | block_half(object, initial_filters = 2, kernel_size = c(3, 3, 3),
num_steps = 1, batch_normalization = FALSE, dropout = 0,
use_maxpooling = TRUE, activation = "relu")
|
object |
( |
initial_filters |
(numeric) Number of filters in the first convolutional layer, Default: 2 |
kernel_size |
(list or vector) size of the convolution kernels, Default: c(3, 3, 3) |
num_steps |
(integer) Number of steps to perform downsampling, Default: 1 if |
activation |
(character) Activation function in the block layers, Default: 'relu' |
In each step, the number of filters is doubled wrt the previous step. Thus, if initial_filters == 2
, the number of filters in the layers in this block is: 2, 4, 8, 16...
The composed object.
block_upsample block_unet
Other blocks: block_double
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.