contrib.nn.deprecated_flipped_sigmoid_cross_entropy_with_logits
tf.contrib.nn.deprecated_flipped_sigmoid_cross_entropy_with_logits
tf.contrib.nn.deprecated_flipped_sigmoid_cross_entropy_with_logits
deprecated_flipped_sigmoid_cross_entropy_with_logits( logits, targets, name=None )
Defined in tensorflow/contrib/nn/python/ops/cross_entropy.py
.
Computes sigmoid cross entropy given logits
.
This function diffs from tf.nn.sigmoid_cross_entropy_with_logits only in the argument order.
Measures the probability error in discrete classification tasks in which each class is independent and not mutually exclusive. For instance, one could perform multilabel classification where a picture can contain both an elephant and a dog at the same time.
For brevity, let x = logits
, z = targets
. The logistic loss is
z * -log(sigmoid(x)) + (1 - z) * -log(1 - sigmoid(x)) = z * -log(1 / (1 + exp(-x))) + (1 - z) * -log(exp(-x) / (1 + exp(-x))) = z * log(1 + exp(-x)) + (1 - z) * (-log(exp(-x)) + log(1 + exp(-x))) = z * log(1 + exp(-x)) + (1 - z) * (x + log(1 + exp(-x)) = (1 - z) * x + log(1 + exp(-x)) = x - x * z + log(1 + exp(-x))
For x < 0, to avoid overflow in exp(-x), we reformulate the above
x - x * z + log(1 + exp(-x)) = log(exp(x)) - x * z + log(1 + exp(-x)) = - x * z + log(1 + exp(x))
Hence, to ensure stability and avoid overflow, the implementation uses this equivalent formulation
max(x, 0) - x * z + log(1 + exp(-abs(x)))
logits
and targets
must have the same type and shape.
Args:
-
logits
: ATensor
of typefloat32
orfloat64
. -
targets
: ATensor
of the same type and shape aslogits
. -
name
: A name for the operation (optional).
Returns:
A Tensor
of the same shape as logits
with the componentwise logistic losses.
Raises:
-
ValueError
: Iflogits
andtargets
do not have the same shape.
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/contrib/nn/deprecated_flipped_sigmoid_cross_entropy_with_logits