tensorflow 2 学习笔记

最新推荐文章于 2024-11-02 15:56:51 发布

鬼谷子2008

最新推荐文章于 2024-11-02 15:56:51 发布

阅读量327

点赞数

文章标签： tensorflow 学习 python

本文链接：https://blog.csdn.net/guiguzi20080808/article/details/126685323

版权

本文详细介绍了TensorFlow中用于计算平均值的tf.math.reduce_mean函数，通过实例解析了该函数在不同维度上的应用，包括axis参数的设置对结果的影响，以及keepdims选项的作用。无论你是初学者还是进阶者，都能从中了解如何在实际操作中有效地使用这个函数。

摘要由CSDN通过智能技术生成

tensorflow学习
求期望值：tf.math.reduce_mean(
input_tensor, The tensor to reduce. Should have numeric type.
输入tensor
axis=None, The dimensions to reduce. If None (the default),
reduces all dimensions. Must be in the range [-
rank(input_tensor),rank(input_tensor)).
默认为None，所有的行列数据取平均。
从最外层区分，0指最外层，1：第二层…
例1：
[ [1,2], [3,4] ], axis=0: ( [1, 2] + [3, 4])/2 = [2, 3], axis = 1: [ [(1+2)/2], [(3+4)/2]
例2：
X =[ axis = 0
[ axis = 1
[ axis = 2
[ 1, 2 ], axis =3
[ 3, 4 ]
] ,
[ [ 5, 6 ],
[ 7, 8 ]
]
],

									  			 [      
									  			 		 [
									  			 		 		 [8,  7 ],
									  			 		 		 [6,  5 ] 
									  			 		 ] ,       
								               			[ 		[ 4, 3 ],
								               					[ 2, 1 ] 
								               			] 
								               	]
								  ]
								 # axis = 0  [[[4,5,4.5],[4.5,4,5]],[[4.5,4.5],[4.5,4.5]]]  shape(2,2,2)
								 # axis = 1 [[[3,4],[5,6]], [[6，5][4,3]]]   avg([1,2] [5,6])  avg([3,4], [7,8]) , avg([8,7],[4,3]), avg([6,5],[2,1])
								 # axis = 2 [[[2,3],[6,7]],[[7,6][3,2]]]   avg(1,3) (2,4) (5,7) (6,8) avg(8,6) (7,5) (4,2)(3,1)
								 # axis = 3 [[[1.5,3.5][5.5,7.5]],[[7.5,5.5][3.5,1.5]]] avg(1,2)(3,4)(5,6)(7,8) avg(7,8)(6,5)(4,3)(2,1)

keepdims=False, If true, retains reduced dimensions with length 1
name=None A name for the operation (optional).
)