torch (version 0.2.0)

nn_max_unpool3d: Computes a partial inverse of MaxPool3d.

Description

MaxPool3d is not fully invertible, since the non-maximal values are lost. MaxUnpool3d takes in as input the output of MaxPool3d including the indices of the maximal values and computes a partial inverse in which all non-maximal values are set to zero.

Usage

nn_max_unpool3d(kernel_size, stride = NULL, padding = 0)

Arguments

kernel_size

(int or tuple): Size of the max pooling window.

stride

(int or tuple): Stride of the max pooling window. It is set to kernel_size by default.

padding

(int or tuple): Padding that was added to the input

Inputs

• input: the input Tensor to invert

• indices: the indices given out by nn_max_pool3d()

• output_size (optional): the targeted output size

Shape

• Input: \((N, C, D_{in}, H_{in}, W_{in})\)

• Output: \((N, C, D_{out}, H_{out}, W_{out})\), where

$$ D_{out} = (D_{in} - 1) \times \mbox{stride[0]} - 2 \times \mbox{padding[0]} + \mbox{kernel\_size[0]} $$ $$ H_{out} = (H_{in} - 1) \times \mbox{stride[1]} - 2 \times \mbox{padding[1]} + \mbox{kernel\_size[1]} $$ $$ W_{out} = (W_{in} - 1) \times \mbox{stride[2]} - 2 \times \mbox{padding[2]} + \mbox{kernel\_size[2]} $$

or as given by output_size in the call operator

Examples

# NOT RUN {
if (torch_is_installed()) {
  
# pool of square window of size=3, stride=2
pool <- nn_max_pool3d(3, stride=2, return_indices=TRUE)
unpool <- nn_max_unpool3d(3, stride=2)
out <- pool(torch_randn(20, 16, 51, 33, 15))
unpooled_output <- unpool(out[[1]], out[[2]])
unpooled_output$size()

}
# }