tf.Reducemean

tf.reducemean

前言

tf.reducemean是一类常见的计算属于Reduction类，这一类的API类似。下面主要看看tf.reducemean的用法和理解

官方

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

Computes the mean of elements across dimensions of a tensor.

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

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

Args：
- input_tensor: The tensor to reduce. Should have numeric type.
- reduction_indices: The dimensions to reduce. If None (the defaut), reduces all dimensions.
- keep_dims: If true, retains reduced dimensions with length 1.
- name: A name for the operation (optional).

Returns:
The reduced tensor.

例子

import numpy as np 
import tensorflow as tf

inputs = [[1, 0, 2],
          [3, 2, 4]]
inputs = np.array(inputs) 
A = tf.reduce_mean(inputs) 
B = tf.reduce_mean(inputs, reduction_indices=0) 
C = tf.reduce_mean(inputs, reduction_indices=1) 
D = tf.reduce_mean(inputs, 0, keep_dims=True) 
E = tf.reduce_mean(inputs, 1, keep_dims=True) 
with tf.Session() as sess:
    print(sess.run(A))
    print(sess.run(B))
    print(sess.run(C))
    print(sess.run(D))
    print(sess.run(E))

结果

理解

（图片摘自知乎）

1. reduction_indices在Martix中可以为none，0，1。none即是求tensor的mean；0则是求column列的mean，因此压缩为一行；而1则是求row行的mean，因此压缩为一列。
2. reduction_indices为1的时候虽然计算的是行压缩为列，应该是以列输出，当是在实验中可以观测到实际以行在输出。若要以列输出，可以让keep_dims = true（例子E）

Reference

• 知乎：凡心的回答
• 官方文档：Math
• 小妖精Fsky’s CSDN BLOG