tf.reduce_sum()_tf.reduce_mean()_tf.reduce_max()

根據官方文檔：

reduce_sum應該理解為壓縮求和，用於降維

 

tf.reduce_sum(input_tensor,axis=None,keepdims=None,name=None,reduction_indices=None,keep_dims=None）

 

Args:

• input_tensor: The tensor to reduce. Should have numeric type. #輸入
• axis: The dimensions to reduce. If None (the default), reduces all dimensions. Must be in the range （rank(input_tensor), rank(input_tensor)).#取0第一維，取1第二維，取-1最后一維
• keepdims: If true, retains reduced dimensions with length 1.#按照原來的維度
• name: A name for the operation (optional).
• reduction_indices: The old (deprecated) name for axis.#axis的原來的名字
• keep_dims: Deprecated alias for keepdims.

  import tensorflow as tf
  import numpy as np
   
  x = tf.constant([[1,1,1],[2,2,2]])
  with tf.Session() as sess:
      print(sess.run(tf.reduce_sum(x))) #所有求和
      print(sess.run(tf.reduce_sum(x,0))) #按 列 求和
      print(sess.run(tf.reduce_sum(x,1))) #按 行 求和
      print(sess.run(tf.reduce_sum(x,1,keepdims=True))) #按維度 行 求和
      print(sess.run(tf.reduce_sum(x,[0,1])))  #行列求和
      print(sess.run(tf.reduce_sum(x,reduction_indices=[1])))
      

  輸出結果：

  9
  [3 3 3]
  [3 6]
  [[3]
   [6]]
  9
  [3 6]

  求最大值tf.reduce_max(input_tensor, reduction_indices=None, keep_dims=False, name=None)

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

  參數1--input_tensor:待求值的tensor。

  參數2--reduction_indices:在哪一維上求解。

  參數（3）（4）可忽略

 

import tensorflow as tf
import numpy as np
 
x = tf.constant([[1,2],[3,4]])
with tf.Session() as sess:
    print(sess.run(tf.reduce_mean(x))) #所有求平均
    print(sess.run(tf.reduce_mean(x, 0))) #按 列 求和
    print(sess.run( tf.reduce_mean(x, 1)))#按行求平均
    print(sess.run(tf.reduce_max(x)))
    print(sess.run(tf.reduce_max(x, 0)))
    print(sess.run(tf.reduce_max(x, 1)))

###############輸出##########
2
[2 3]
[1 3]
4
[3 4]
[2 4]