torch (version 0.8.1)

nn_dropout2d: Dropout2D module

Description

Randomly zero out entire channels (a channel is a 2D feature map, e.g., the \(j\)-th channel of the \(i\)-th sample in the batched input is a 2D tensor \(\mbox{input}[i, j]\)).

Usage

nn_dropout2d(p = 0.5, inplace = FALSE)

Arguments

p

(float, optional): probability of an element to be zero-ed.

inplace

(bool, optional): If set to TRUE, will do this operation in-place

Shape

• Input: \((N, C, H, W)\)

• Output: \((N, C, H, W)\) (same shape as input)

Details

Each channel will be zeroed out independently on every forward call with probability p using samples from a Bernoulli distribution. Usually the input comes from nn_conv2d modules.

As described in the paper Efficient Object Localization Using Convolutional Networks , if adjacent pixels within feature maps are strongly correlated (as is normally the case in early convolution layers) then i.i.d. dropout will not regularize the activations and will otherwise just result in an effective learning rate decrease. In this case, nn_dropout2d will help promote independence between feature maps and should be used instead.

Examples

if (torch_is_installed()) {
m <- nn_dropout2d(p = 0.2)
input <- torch_randn(20, 16, 32, 32)
output <- m(input)
}