# -- encoding:utf-8 --

import tensorflow as tf

# 定义常量矩阵a(dype类型为常量,shape可构建矩阵类型)a = tf.constant([[1,2],[3,4]],dtype=tf.int32)b = tf.constant([5,6,7,8],dtype=tf.int32,shape=[2,2])# 以a,b作为输入，进行矩阵的乘法操作matmulc = tf.matmul(a,b)g = tf.add(a,c)

#op之间如果没有依赖关系，会并行处理#调用session的run方法来执行矩阵

#log_device_placement是否打日志，默认不打日志#allow_soft_placement是否动态使用CPU和GPU，默认为Falsewith tf.Session(config=tf.ConfigProto(log_device_placement=True,allow_soft_placement=True)) as sess1:    result = sess1.run(g)    # 结果是多个值，返回一个列表    # result = sess.run(fetches=[c,g])    print('type:{},value:{}'.format(type(result), result))

# -- encoding:utf-8 --

import tensorflow as tf#定义一个变量w1w1 = tf.Variable(initial_value=3.0,dtype=tf.float32,name='w1')#定义一个常量a =tf.constant(value=2.0,dtype=tf.float32,name='w1')#定义一个变量w2w2 = tf.Variable(w1.initialized_value() * a,name='w2')

c = tf.add(w1,w2)#进行全局变量初始化init_op = tf.global_variables_initializer()

with tf.Session(config=tf.ConfigProto(log_device_placement=True)) as sess:    sess.run(init_op)    result = sess.run(c)    print("result:{}".format(result))

# -- encoding:utf-8 --import tensorflow as tf#构建一个矩阵的乘法，但是矩阵在运行的时候给定#dtype、shape、name
m1 = tf.placeholder(dtype=tf.float32,shape=[2,3],name='placeholder_m1')
m2 = tf.placeholder(dtype=tf.float32,shape=[3,2],name='placeholder_m2')
m3 = tf.matmul(m1,m2)init_op = tf.global_variables_initializer()with tf.Session(config=tf.ConfigProto(log_device_placement=True)) as sess:sess.run(init_op)result = sess.run(fetches=[m3],feed_dict={m1: [[1,2,3],[4,5,6]],m2: [[1,2],[3,4],[5,6]]})print('result:{}'.format(result))

import tensorflow as tfa = tf.Variable(initial_value=0,dtype=tf.int32,name='v_x')
#变量a的更新
assign_op = tf.assign(ref = a,value = a+1)init_op = tf.global_variables_initializer()with tf.Session(config=tf.ConfigProto(log_device_placement=True)) as sess:sess.run(init_op)for i in range(5):r_x = sess.run(a)sess.run(assign_op)print(r_x)