mindspore.nn.Dropout3d

class mindspore.nn.Dropout3d(p=0.5)[source]

During training, randomly zeroes some channels of the input tensor with probability p from a Bernoulli distribution (For a 5-dimensional tensor with a shape of \(NCDHW\), the channel feature map refers to a 3-dimensional feature map with a shape of \(DHW\)).

For example, the \(j\_th\) channel of the \(i\_th\) sample in the batched input is a to-be-processed 3D tensor input[i,j]. Each channel will be zeroed out independently on every forward call which based on Bernoulli distribution probability p.

Dropout3d can improve the independence between channel feature maps.

Refer to mindspore.ops.dropout3d() for more details.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor, nn
>>> import numpy as np
>>> dropout = nn.Dropout3d(p=0.5)
>>> x = Tensor(np.ones([2, 1, 2, 1, 2]), mindspore.float32)
>>> output = dropout(x)
>>> print(output.shape)
(2, 1, 2, 1, 2)