mindspore.nn.Dropout2d

class mindspore.nn.Dropout2d(p=0.5)

During training, randomly zeroes some channels of the input tensor with probability p from a Bernoulli distribution (For a 4-dimensional tensor with a shape of $NCHW$, the channel feature map refers to a 2-dimensional feature map with the shape of $HW$).

For example, the $j\mathrm{\_}th$ channel of the $i\mathrm{\_}th$ sample in the batched input is a to-be-processed 2D tensor input[i,j]. At each forward propagation, each channel will be independently determined to be set to zero with probability p.

Dropout2d can improve the independence between channel feature maps.

Refer to mindspore.ops.dropout2d() for more details.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor, nn
>>> import numpy as np
>>> dropout = nn.Dropout2d(p=0.5)
>>> x = Tensor(np.ones([2, 1, 2, 3]), mindspore.float32)
>>> output = dropout(x)
>>> print(output.shape)
(2, 1, 2, 3)