View source on GitHub
|
View source on GitHub
|
Categorical crossentropy between an output tensor and a target tensor.
tf.keras.backend.categorical_crossentropy(
target, output, from_logits=False, axis=-1
)
target: A tensor of the same shape as output.output: A tensor resulting from a softmax
(unless from_logits is True, in which
case output is expected to be the logits).from_logits: Boolean, whether output is the
result of a softmax, or is a tensor of logits.axis: Int specifying the channels axis. axis=-1 corresponds to data
format channels_last', andaxis=1corresponds to data format
channels_first`.Output tensor.
ValueError: if axis is neither -1 nor one of the axes of output.>>> a = tf.constant([1., 0., 0., 0., 1., 0., 0., 0., 1.], shape=[3,3])
>>> print(a)
tf.Tensor(
[[1. 0. 0.]
[0. 1. 0.]
[0. 0. 1.]], shape=(3, 3), dtype=float32)
>>> b = tf.constant([.9, .05, .05, .5, .89, .6, .05, .01, .94], shape=[3,3])
>>> print(b)
tf.Tensor(
[[0.9 0.05 0.05]
[0.5 0.89 0.6 ]
[0.05 0.01 0.94]], shape=(3, 3), dtype=float32)
>>> loss = tf.keras.backend.categorical_crossentropy(a, b)
>>> print(loss)
tf.Tensor([0.10536055 0.8046684 0.06187541], shape=(3,), dtype=float32)
>>> loss = tf.keras.backend.categorical_crossentropy(a, a)
>>> print(loss)
tf.Tensor([1.1920929e-07 1.1920929e-07 1.19...e-07], shape=(3,),
dtype=float32)