torch.nn.functional.dropout3d#

torch.nn.functional.dropout3d(input,p=0.5,training=True,inplace=False)[source]#

Randomly zero out entire channels (a channel is a 3D feature map).

For example, the$j$j-th channel of the$i$i-th sample in thebatched input is a 3D tensor$\text{input}[i,j]$input[i,j] of the input tensor.Each channel will be zeroed out independently on every forward call withprobabilityp using samples from a Bernoulli distribution.

SeeDropout3d for details.

Parameters

• p (float) – probability of a channel to be zeroed. Default: 0.5

• training (bool) – apply dropout if isTrue. Default:True

• inplace (bool) – If set toTrue, will do this operation in-place. Default:False

Return type

Tensor