SparseSoftmaxCrossEntropy#
SparseSoftmaxCrossEntropy - 9#
Version
domain: main
since_version: 9
function:
support_level:
shape inference:
This version of the operator has been available since version 9.
Summary
SparseSoftmaxCrossEntropy
Attributes
reduction: Type of reduction to apply to loss: none, sum, mean(default). ‘none’: the output is the loss for each sample in the batch.’sum’: the output will be summed. ‘mean’: the sum of the output will be divided by the batch_size. Default value is
?.
Inputs
Between 2 and 3 inputs.
logits (heterogeneous) - T: Unscaled log probabilities, (N+1)-D input of shape (-1, num_classes).
label (heterogeneous) - Tind: label is N-D input whose shape should match that of logits. It is a tensor of nonnegative integers, where each element is the nonnegative integer label for the element of the batch.
weight (optional, heterogeneous) - T: weight for each sample. The shape is the same as label’s
Outputs
Between 1 and 2 outputs.
Y (heterogeneous) - T: loss.
log_prob (optional, heterogeneous) - T: logsoftmax(logits)
Examples