|View source on GitHub|
Computes softmax cross entropy between
tf.compat.v2.nn.softmax_cross_entropy_with_logits( labels, logits, axis=-1, name=None )
Measures the probability error in discrete classification tasks in which the classes are mutually exclusive (each entry is in exactly one class). For example, each CIFAR-10 image is labeled with one and only one label: an image can be a dog or a truck, but not both.
NOTE: While the classes are mutually exclusive, their probabilities
need not be. All that is required is that each row of
a valid probability distribution. If they are not, the computation of the
gradient will be incorrect.
If using exclusive
labels (wherein one and only
one class is true at a time), see
WARNING: This op expects unscaled logits, since it performs a
logits internally for efficiency. Do not call this op with the
softmax, as it will produce incorrect results.
A common use case is to have logits and labels of shape
[batch_size, num_classes], but higher dimensions are supported, with
axis argument specifying the class dimension.
labels must have the same dtype (either
Backpropagation will happen into both
labels. To disallow
labels, pass label tensors through
before feeding it to this function.
Note that to avoid confusion, it is required to pass only named arguments to this function.
labels: Each vector along the class dimension should hold a valid probability distribution e.g. for the case in which labels are of shape
[batch_size, num_classes], each row of
labels[i]must be a valid probability distribution.
logits: Per-label activations, typically a linear output. These activation energies are interpreted as unnormalized log probabilities.
axis: The class dimension. Defaulted to -1 which is the last dimension.
name: A name for the operation (optional).
Tensor that contains the softmax cross entropy loss. Its type is the
logits and its shape is the same as
labels except that it does
not have the last dimension of