tf.reduce_logsumexp( input_tensor, axis=None, keepdims=None, name=None, reduction_indices=None, keep_dims=None )
See the guide: Math > Reduction
Computes log(sum(exp(elements across dimensions of a tensor))). (deprecated arguments)
SOME ARGUMENTS ARE DEPRECATED. They will be removed in a future version. Instructions for updating: keep_dims is deprecated, use keepdims instead
input_tensor along the dimensions given in
keepdims is true, the rank of the tensor is reduced by 1 for each
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)
input_tensor: The tensor to reduce. Should have numeric type.
axis: The dimensions to reduce. If
None(the default), reduces all dimensions. Must be in the range
keepdims: If true, retains reduced dimensions with length 1.
name: A name for the operation (optional).
reduction_indices: The old (deprecated) name for axis.
keep_dims: Deprecated alias for
The reduced tensor.