View source on GitHub |
Computes sparse softmax cross entropy between logits
and labels
.
tf.nn.sparse_softmax_cross_entropy_with_logits(
labels, logits, 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.
A common use case is to have logits of shape
[batch_size, num_classes]
and have labels of shape
[batch_size]
, but higher dimensions are supported, in which
case the dim
-th dimension is assumed to be of size num_classes
.
logits
must have the dtype of float16
, float32
, or float64
, and
labels
must have the dtype of int32
or int64
.
logits = tf.constant([[2., -5., .5, -.1],
[0., 0., 1.9, 1.4],
[-100., 100., -100., -100.]])
labels = tf.constant([0, 3, 1])
tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=labels, logits=logits).numpy()
array([0.29750752, 1.1448325 , 0. ], dtype=float32)
To avoid confusion, passing only named arguments to this function is recommended.
Returns | |
---|---|
A Tensor of the same shape as labels and of the same type as logits
with the softmax cross entropy loss.
|
Raises | |
---|---|
ValueError
|
If logits are scalars (need to have rank >= 1) or if the rank of the labels is not equal to the rank of the logits minus one. |