简而言之,reduce系列的函数都可在张量指定的维度上操作
目录
输入参数
tf.reduce_all 在boolean张量的维度上计算元素的 "逻辑和"
tf.reduce_any 在boolean张量的维度上计算元素的 "逻辑或"
tf.reduce_max 计算张量的各个维度上元素的最大值
tf.reduce_min 计算张量的各个维度上元素的最小值
tf.reduce_mean 计算张量的各个维度上的元素的平均值
tf.reduce_sum 计算张量的各个维度上元素的总和
tf.reduce_prod 计算张量的各个维度上元素的乘积
tf.reduce_logsumexp 计算log(sum(exp(张量的各维数的元素)))
tf.reduce_join 在给定的维度上加入一个字符串张量
tf.reduce_all/reduce_any/reduce_max/reduce_min/reduce_mean/reduce_sum/reduce_prod/reduce_logsumexp(
input_tensor,
axis=None,
keepdims=None,
name=None,
reduction_indices=None,
keep_dims=None
)
按照axis给定的维度减少input_tensor (boolean Tensor) 。除非keepdims为 true,否则张量的秩将在轴的每个条目中减少1。如果keep_dims为 true,则减小的维度将保留为长度1。
如果axis=None,则会减少所有维度,并返回具有单个元素的张量。
x = tf.constant([[True, True], [False, False]])
tf.reduce_all(x) # False
tf.reduce_all(x, 0) # [False, False]
tf.reduce_all(x, 1) # [True, False]
x = tf.constant([[True, True], [False, False]])
tf.reduce_any(x) # True
tf.reduce_any(x, 0) # [True, True]
tf.reduce_any(x, 1) # [True, False]
x = tf.constant([[1, 2, 3], [4, 5, 6]])
tf.reduce_max(x) # 6
tf.reduce_max(x, 0) # [4, 5, 6]
tf.reduce_max(x, 1) # [3, 6]
tf.reduce_max(x, 1, keepdims=True) # [[3],
# [6]]
tf.reduce_max(x, [0, 1]) # 6
x = tf.constant([[1, 2, 3], [4, 5, 6]])
tf.reduce_min(x) # 1
tf.reduce_min(x, 0) # [1, 2, 3]
tf.reduce_min(x, 1) # [1, 4]
tf.reduce_min(x, 1, keepdims=True) # [[1],
# [4]]
tf.reduce_min(x, [0, 1]) # 1
x = tf.constant([[1., 2., 3], [4., 5., 6.]])
tf.reduce_mean(x) # 3.5
tf.reduce_mean(x, 0) # [2.5, 3.5, 4.5]
tf.reduce_mean(x, 1) # [2., 5.]
tf.reduce_mean(x, 1, keepdims=True) # [[2.],
# [5.]]
tf.reduce_mean(x, [0, 1]) # 3.5
要注意数据类型的兼容性
x = tf.constant([1, 0, 1, 0])
tf.reduce_mean(x) # 0
y = tf.constant([1., 0., 1., 0.])
tf.reduce_mean(y) # 0.5
x = tf.constant([[1, 2, 3], [4, 5, 6]])
tf.reduce_sum(x) # 21
tf.reduce_sum(x, 0) # [5, 7, 9]
tf.reduce_sum(x, 1) # [6, 15]
tf.reduce_sum(x, 1, keepdims=True) # [[ 6],
# [15]]
tf.reduce_sum(x, [0, 1]) # 21
x = tf.constant([[1, 2, 3], [4, 5, 6]])
tf.reduce_prod(x) # 720
tf.reduce_prod(x, 0) # [4, 10, 18]
tf.reduce_prod(x, 1) # [6, 120]
tf.reduce_prod(x, 1, keepdims=True) # [[ 6],
# [120]]
tf.reduce_prod(x, [0, 1]) # 720
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)
这个函数在数值上比 更稳定。它避免了大量输入的 exp 引起的溢出和小输入日志带来的下溢。
tf.reduce_join(
inputs,
axis=None,
keep_dims=False,
separator='',
name=None,
reduction_indices=None
)
# tensor `a` is [["a", "b"], ["c", "d"]]
tf.reduce_join(a, 0) # ==> ["ac", "bd"]
tf.reduce_join(a, 1) # ==> ["ab", "cd"]
tf.reduce_join(a, -2) # = tf.reduce_join(a, 0) ==> ["ac", "bd"]
tf.reduce_join(a, -1) # = tf.reduce_join(a, 1) ==> ["ab", "cd"]
tf.reduce_join(a, 0, keep_dims=True) # ==> [["ac", "bd"]]
tf.reduce_join(a, 1, keep_dims=True) # ==> [["ab"], ["cd"]]
tf.reduce_join(a, 0, separator=".") # ==> ["a.c", "b.d"]
tf.reduce_join(a, [0, 1]) # ==> "acbd"
tf.reduce_join(a, [1, 0]) # ==> "abcd"
tf.reduce_join(a, []) # ==> [["a", "b"], ["c", "d"]]
tf.reduce_join(a) # = tf.reduce_join(a, [1, 0]) ==> "abcd"
在具有给定形状的 字符串张量中计算跨维度的字符串连接。返回一个新的Tensor,它由输入字符串与给定的分隔符separator(默认:空字符串)连接创建的。axis为负则从末端向后数,-1相当于n - 1。