tf.accumulate_n( inputs, shape=None, tensor_dtype=None, name=None )
See the guide: Math > Reduction
Returns the element-wise sum of a list of tensors.
tensor_dtype for shape and type checking,
otherwise, these are inferred.
tf.accumulate_n performs the same operation as
tf.add_n, but does not
wait for all of its inputs to be ready before beginning to sum. This can
save memory if inputs are ready at different times, since minimum temporary
storage is proportional to the output size rather than the inputs size.
accumulate_n is differentiable (but wasn't previous to TensorFlow 1.7).
a = tf.constant([[1, 2], [3, 4]]) b = tf.constant([[5, 0], [0, 6]]) tf.accumulate_n([a, b, a]) # [[7, 4], [6, 14]] # Explicitly pass shape and type tf.accumulate_n([a, b, a], shape=[2, 2], tensor_dtype=tf.int32) # [[7, 4], # [6, 14]]
inputs: A list of
Tensorobjects, each with same shape and type.
shape: Shape of elements of
tensor_dtype: The type of
name: A name for the operation (optional).
Tensor of same shape and type as the elements of
inputsdon't all have same shape and dtype or the shape cannot be inferred.