mindspore.ops.BinaryCrossEntropy

class mindspore.ops.BinaryCrossEntropy(*args, **kwargs)[source]

Computes the binary cross entropy between the target and the output.

Sets input as \(x\), input label as \(y\), output as \(\ell(x, y)\). Let,

\[L = \{l_1,\dots,l_N\}^\top, \quad l_n = - w_n \left[ y_n \cdot \log x_n + (1 - y_n) \cdot \log (1 - x_n) \right]\]

Then,

\[\begin{split}\ell(x, y) = \begin{cases} L, & \text{if reduction} = \text{'none';}\\ \operatorname{mean}(L), & \text{if reduction} = \text{'mean';}\\ \operatorname{sum}(L), & \text{if reduction} = \text{'sum'.} \end{cases}\end{split}\]
Parameters

reduction (str) – Specifies the reduction to be applied to the output. Its value must be one of ‘none’, ‘mean’, ‘sum’. Default: ‘mean’.

Inputs:

  • input_x (Tensor) - The input Tensor. The data type must be float16 or float32.

  • input_y (Tensor) - The label Tensor which has same shape and data type as input_x.

  • weight (Tensor, optional) - A rescaling weight applied to the loss of each batch element. And it must have same shape and data type as input_x. Default: None.

Outputs:

Tensor or Scalar, if reduction is ‘none’, then output is a tensor and has the same shape as input_x. Otherwise, the output is a scalar.

Raises

  • TypeError – If dtype of input_x, input_y or weight (if given) is neither float16 not float32.

  • ValueError – If reduction is not one of ‘none’, ‘mean’, ‘sum’.

  • ValueError – If shape of input_y is not the same as input_x or weight (if given).

  • TypeError – If input_x, input_y or weight is not a Tensor.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import mindspore.nn as nn
>>> import numpy as np
>>> from mindspore import Tensor
>>> from mindspore.ops import operations as ops
>>> class Net(nn.Cell):
...     def __init__(self):
...         super(Net, self).__init__()
...         self.binary_cross_entropy = ops.BinaryCrossEntropy()
...     def construct(self, x, y, weight):
...         result = self.binary_cross_entropy(x, y, weight)
...         return result
...
>>> net = Net()
>>> input_x = Tensor(np.array([0.2, 0.7, 0.1]), mindspore.float32)
>>> input_y = Tensor(np.array([0., 1., 0.]), mindspore.float32)
>>> weight = Tensor(np.array([1, 2, 2]), mindspore.float32)
>>> output = net(input_x, input_y, weight)
>>> print(output)
0.38240486