tf.reducemean()到底是什么意思？

https://blog.csdn.net/he_min/article/details/78694383

在tensorflow中經常見到reducemean這個api,到底有什么用，到底是對誰求均值？

api中是這樣寫的：

tf.reduce_mean(input_tensor, axis=None, keep_dims=False, name=None, reduction_indices=None)

Computes the mean of elements across dimensions 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.

直觀的翻譯就是

根據給出的axis在input_tensor上求平均值。除非keep_dims為真，axis中的每個的張量秩會減少1。如果keep_dims為真，求平均值的維度的長度都會保持為1.如果不設置axis，所有維度上的元素都會被求平均值，並且只會返回一個只有一個元素的張量。

為了更加清楚的理解其含義，給出一個簡單的例子：

import tensorflow as tf

import numpy as np

'''
x = [[1.,2.],[3.,4.]]

print(tf.reduce_mean(x))
print(tf.reduce_mean(x,0))
print(tf.reduce_mean(x,1))
'''
x = np.array([[1.,2.,3.],[4.,5.,6.]])

with tf.Session() as sess:
    #返回所有元素的平均值
    mean_none = sess.run(tf.reduce_mean(x))
    #返回各列的平均值
    mean_0 = sess.run(tf.reduce_mean(x, 0))
    #返回各行的平均值向量
    mean_1 = sess.run(tf.reduce_mean(x, 1))

    print(x)
    print(mean_none)
    print(mean_0)
    print(mean_1)