mindspore.mint.nn.functional.dropout

mindspore.mint.nn.functional.dropout(input, p=0.5, training=True, inplace=False)[source]

During training, randomly zeroes some of the elements of the input tensor with probability p from a Bernoulli distribution. It plays the role of reducing neuron correlation and avoid overfitting. And the return will be multiplied by \(\frac{1}{1-p}\) during training. During the reasoning, this operation returns the same Tensor as the input.

Parameters

input (Tensor) – The input Tensor of shape \((*, N)\).
p (float) – The dropping rate of input neurons, between 0 and 1, e.g. p = 0.1, means dropping out 10% of input neurons. Default: 0.5 .
training (bool) – Apply dropout if it is True , if it is False , the input is returned directly, and p is invalid. Default: True .
inplace (bool) – If set to True , will do this operation in-place. Default: False .

Returns

output (Tensor) - Zeroed tensor, with the same shape and data type as input.

Raises

TypeError – If p is not a float.
TypeError – If input is not a Tensor.

Supported Platforms:: Ascend

Examples

>>> import mindspore
>>> from mindspore import Tensor, mint
>>> input = Tensor(((20, 16), (50, 50)), mindspore.float32)
>>> output = mint.nn.functional.dropout(input, p=0.5)
>>> print(output.shape)
(2, 2)