TensorFlow函数

tf.reduce_sum(tensor)

方法代码和注解：

def reduce_sum(input_tensor,
               axis=None,
               keep_dims=False,
               name=None,
               reduction_indices=None):
  """Computes the sum of elements across dimensions（[数] 维） of a tensor.

  Reduces `input_tensor` along the dimensions given in `axis`.
  Unless `keep_dims` is true, the rank of the tensor is reduced by 1 for each
  entry in `axis`. If `keep_dims` is true, the reduced dimensions
  are retained with length 1.

  If `axis` has no entries, all dimensions are reduced, and a
  tensor with a single element is returned.

  For example:

  ```python
  x = tf.constant([[1, 1, 1], [1, 1, 1]])
  tf.reduce_sum(x)  # 6
  tf.reduce_sum(x, 0)  # [2, 2, 2]
  tf.reduce_sum(x, 1)  # [3, 3]
  tf.reduce_sum(x, 1, keep_dims=True)  # [[3], [3]]
  tf.reduce_sum(x, [0, 1])  # 6

  Args:
    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
      `[-rank(input_tensor), rank(input_tensor))`.
    keep_dims: If true, retains reduced dimensions with length 1.
    name: A name for the operation (optional).
    reduction_indices: The old (deprecated) name for axis.

  Returns:
    The reduced tensor.

  @compatibility(numpy)
  Equivalent to np.sum
  @end_compatibility
  """
  return gen_math_ops._sum(
      input_tensor,
      _ReductionDims(input_tensor, axis, reduction_indices),
      keep_dims,
      name=name)

tesnor可以理解为多维数组

import tensorflow as tf
import inspect
import re

# get var_name
def varname(var):
  for line in inspect.getframeinfo(inspect.currentframe().f_back)[3]:
    m = re.search(r'\bvarname\s*\(\s*([A-Za-z_][A-Za-z0-9_]*)\s*\)', line)
    if m:
      return m.group(1)

# print var and var_name
def printNameAndValue(var_name,var):
    print("%s : %s;" % (var_name,tf.Session().run(var)))

# y : a rank 3 tensor with shape [2,3,4]
y = tf.constant([[[1,1,1,1], [1,1,1,1], [1,1,1,1]], [[1,1,1,1], [1,1,1,1], [1,1,1,1]]])   
tf.reduce_sum(y, 0)     # [[2 2 2 2],[2 2 2 2],[2 2 2 2]]           a rank 2 tensor with shape [3,4]
tf.reduce_sum(y,1)      # [[3 3 3 3],[3 3 3 3]]                     a rank 2 tensor with shape [2,4]
tf.reduce_sum(y,[0,1])  # [6 6 6 6]                                 a rank 1 tensor with shape [4]
tf.reduce_sum(y,1, keep_dims=True)  #[[[3 3 3 3]],[[3 3 3 3]]];     a rank 3 tensor with shape [2,1,4]
tf.reduce_sum(y,0,keep_dims=True) #[[[2 2 2 2],[2 2 2 2],[2 2 2 2]]] a rank 3 tensor with shape [1,3,4]
tf.reduce_sum(y,[0,2],keep_dims=True) # [[[8],[8],[8]]]             a rank 3 tensor with shape [1,1,3]

终结：

1.对input_tensor的某些维度进行合并，keep_dims将会保留tensor的rank（维度）并设置shape对应的维度为1。