相关公式

[0.36424586843872840.6675075448915823]×[0.134750808390697090.5863696301031353]=[0.44048858]

[0.134750808390697090.5863696301031353]×[0.36424586843872840.6675075448915823]=[0.049082430.213582720.089947180.39140615]

结果示例

-08-29 13:45:18,965 - DEBUG - start tensorflow tutorial example 5 matrix multiply operation-08-29 13:45:19,003 - DEBUG - MATRIX_A :[[0.3642458684387284, 0.6675075448915823]]-08-29 13:45:19,019 - DEBUG - MATRIX_B :[[0.13475080839069709], [0.5863696301031353]]-08-29 13:45:19,066 - DEBUG - OPERATION_MATMUL_A_B(PLACEHOLDER_A, PLACEHOLDER_B) :[[ 0.44048858]]-08-29 13:45:19,088 - DEBUG - OPERATION_MATMUL_B_A(PLACEHOLDER_A, PLACEHOLDER_B) :[[ 0.04908243 0.08994718][ 0.21358272 0.39140615]]

源代码

# -*- coding: utf-8 -*-"""filename : tutorial_example_5_matmul_operation.pyauthor: hu@ QQ: 443089607 weixin: huzhenghui weibo: /443089607category : tensorflowtitle : python tensorflow学习笔记（五）矩阵乘法运算csdn blog url :weibo article url :weibo message url :为了清晰直观展现python严格要求的缩进及数学公式，请访问博客上博文详细说明见源代码中的注释"""# standard importimport loggingimport randomimport tensorflowlogging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')logging.debug('start tensorflow tutorial example 5 matrix multiply operation')# 定义一个占位符矩阵，类型为float64，尺寸为一行两列PLACEHOLDER_A = tensorflow.placeholder(tensorflow.float64, [1, 2])# 定义一个占位符矩阵，类型为float64，尺寸为两行一列PLACEHOLDER_B = tensorflow.placeholder(tensorflow.float64, [2, 1])# 定义一个矩阵乘法运算，左A右BOPERATION_MATMUL_A_B = tensorflow.matmul(PLACEHOLDER_A, PLACEHOLDER_B)# 定义一个矩阵乘法运算，左B右AOPERATION_MATMUL_B_A = tensorflow.matmul(PLACEHOLDER_B, PLACEHOLDER_A)# 创建一个会话SESSION = tensorflow.Session()# 一个尺寸为一行两列的矩阵MATRIX_A = [[random.random(), random.random()]]# 一个尺寸为两行一列的矩阵MATRIX_B = [[random.random()],[random.random()]]# 显示尺寸为一行两列的矩阵的值logging.debug('MATRIX_A : \n%s', MATRIX_A)# 显示尺寸为两行一列的矩阵的值logging.debug('MATRIX_B : \n%s', MATRIX_B)# 运行左A右B的矩阵乘法运算，结果是1x1矩阵logging.debug('OPERATION_MATMUL_A_B(PLACEHOLDER_A, PLACEHOLDER_B) : \n%s', SESSION.run(OPERATION_MATMUL_A_B, feed_dict={PLACEHOLDER_A: MATRIX_A, PLACEHOLDER_B: MATRIX_B}))# 运行左B右A的矩阵乘法运算，结果是2x2矩阵logging.debug('OPERATION_MATMUL_B_A(PLACEHOLDER_A, PLACEHOLDER_B) : \n%s', SESSION.run(OPERATION_MATMUL_B_A, feed_dict={PLACEHOLDER_A: MATRIX_A, PLACEHOLDER_B: MATRIX_B}))#end of file