|View source on GitHub|
Computes log(sum(exp(elements across dimensions of a tensor))).
tf.math.reduce_logsumexp( input_tensor, axis=None, keepdims=False, name=None )
input_tensor along the dimensions given in
keepdims is true, the rank of the tensor is reduced by 1 for each of the entries in
axis, which must be unique. If
keepdims is true, the reduced dimensions are retained with length 1.
axis has no entries, all dimensions are reduced, and a tensor with a single element is returned.
This function is more numerically stable than log(sum(exp(input))). It avoids overflows caused by taking the exp of large inputs and underflows caused by taking the log of small inputs.
x = tf.constant([[0., 0., 0.], [0., 0., 0.]]) tf.reduce_logsumexp(x) # log(6) tf.reduce_logsumexp(x, 0) # [log(2), log(2), log(2)] tf.reduce_logsumexp(x, 1) # [log(3), log(3)] tf.reduce_logsumexp(x, 1, keepdims=True) # [[log(3)], [log(3)]] tf.reduce_logsumexp(x, [0, 1]) # log(6)
| ||The tensor to reduce. Should have numeric type.|
| || The dimensions to reduce. If |
| ||If true, retains reduced dimensions with length 1.|
| ||A name for the operation (optional).|
|The reduced tensor.|
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.