mindspore.ops.Dropout

class mindspore.ops.Dropout(keep_prob=0.5, Seed0=0, Seed1=0)

During training, randomly zeroes some of the elements of the input tensor with probability $1-keep\mathrm{\_}prob$ from a Bernoulli distribution. It plays the role of reducing neuron correlation and avoid overfitting.

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

Parameters

• keep_prob (float, optional) – The keep rate, between 0 and 1, e.g. keep_prob = 0.9, means dropping out 10% of input units. Default: 0.5 .

• Seed0 (int, optional) – Seed0 value for random generating. Default: 0 .

• Seed1 (int, optional) – Seed1 value for random generating. Default: 0 .

Inputs:

• x (Tensor) - The input Tensor of shape $(\ast ,N)$, with data type of float16, float32 or float64.

Outputs:

• output (Tensor) - With the same shape and data type as x.

• mask (Tensor) - The mask applied to x.

  • On GPU and CPU, mask has the same shape and data type as x.

  • On Ascend, to achieve a better performance, it is denoted as a 1-D Tensor with Uint8 data type. It has shape $(byte\mathrm{\_}counts,)$ where $byte\mathrm{\_}counts$ is the number of bytes needed to mask the input x, $byte\mathrm{\_}counts$ is calculated using the following formula:

    $$byte\mathrm{\_}counts=\text{ceil}(\text{cumprod}(x.shape)/128)\ast 16$$

    If shape of x is $(2,3,4,5,6)$, the shape of mask will be $(96,)$.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> dropout = ops.Dropout(keep_prob=0.5)
>>> x = Tensor(np.ones([1, 2, 3, 4, 5]), mindspore.float32)
>>> output, mask = dropout(x)
>>> print(output.shape, mask.shape, mask.dtype)
(1, 2, 3, 4, 5) (16,) UInt8