mindspore.ops.SparseSoftmaxCrossEntropyWithLogits

class mindspore.ops.SparseSoftmaxCrossEntropyWithLogits(is_grad=False)

Computes the softmax cross-entropy value between logits and sparse encoding labels.

Sets input logits as X, input label as Y, output as loss. The formula is as follows:

$$\begin{array}{r}\begin{array}{l}\\ p_{ij}=softmax(X_{ij})=\frac{\exp (x_i)}{\sum _{j=0}^{N-1}\exp (x_j)}\\ los{s}_{ij}=\{\begin{array}{ll}-ln(p_{ij}),& j=y_i\\ 0,& j\ne y_i\end{array}\\ loss=\sum _{ij}los{s}_{ij}\end{array}\end{array}$$

Parameters

is_grad (bool, optional) – If True , this operation returns the computed gradient. Default: False .

Inputs:

• logits (Tensor) - Input logits, with shape $(N,C)$. Data type must be float16 or float32.

• labels (Tensor) - Ground truth labels, with shape $(N)$. Data type must be int32 or int64.

Outputs:

Tensor, if is_grad is False, the output tensor is the value of loss; if is_grad is True , the output tensor is the gradient of input with the same shape as logits.

Raises

• TypeError – If is_grad is not a bool.

• TypeError – If dtype of logits is neither float16 nor float32.

• TypeError – If dtype of labels is neither int32 nor int64.

• ValueError – If $logits.shape[0]!=labels.shape[0]$.

Supported Platforms:

GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor, ops
>>> logits = Tensor([[2, 3, 1, 4, 5], [2, 1, 2, 4, 3]], mindspore.float32)
>>> labels = Tensor([0, 1], mindspore.int32)
>>> sparse_softmax_cross = ops.SparseSoftmaxCrossEntropyWithLogits()
>>> loss = sparse_softmax_cross(logits, labels)
>>> print(loss)
3.4878292
>>> sparse_softmax_cross_grad = ops.SparseSoftmaxCrossEntropyWithLogits(is_grad=True)
>>> loss_grad = sparse_softmax_cross_grad(logits, labels)
>>> print(loss_grad)
[[-0.48415753  0.04306427  0.00582811  0.11706084  0.3182043 ]
 [ 0.04007946 -0.4852556   0.04007946  0.2961494   0.10894729]]