mindspore.ops.BinaryCrossEntropy

class mindspore.ops.BinaryCrossEntropy(reduction='mean')

Computes the binary cross entropy between the logits and the labels.

Sets logits as $x$, labels as $y$, output as $\ell (x,y)$. Let,

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

In which, $L$ indicates the loss of all batch_sizes, $l$ indicates the loss of one batch_size, and n indicates one batch_size in the 1-N range. Then,

$$\begin{array}{r}\ell (x,y)=\{\begin{array}{ll}L,& \text{if reduction}=\text{'none';}\\ \mathrm{mean}(L),& \text{if reduction}=\text{'mean';}\\ \mathrm{sum}(L),& \text{if reduction}=\text{'sum'.}\end{array}\end{array}$$

Warning

• The value of “x” must range from 0 to 1.

• The value of “y” must be “0” or “1”.

Parameters

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

Inputs:

• logits (Tensor) - The input Tensor. The data type must be float16 or float32, The shape is $(N,\ast )$ where $\ast$ means, any number of additional dimensions.

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

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

Outputs:

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

Raises

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

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

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

• TypeError – If logits, labels or weight is not a Tensor.

Supported Platforms:

Ascend GPU CPU

Examples

>>> class Net(nn.Cell):
...     def __init__(self):
...         super(Net, self).__init__()
...         self.binary_cross_entropy = ops.BinaryCrossEntropy()
...     def construct(self, logits, labels, weight):
...         result = self.binary_cross_entropy(logits, labels, weight)
...         return result
...
>>> net = Net()
>>> logits = Tensor(np.array([0.2, 0.7, 0.1]), mindspore.float32)
>>> labels = Tensor(np.array([0., 1., 0.]), mindspore.float32)
>>> weight = Tensor(np.array([1, 2, 2]), mindspore.float32)
>>> output = net(logits, labels, weight)
>>> print(output)
0.38240486