运行代码
1.
import tensorflow as tf tf.compat.v1.disable_eager_execution() #保证sess.run()能够正常运行 import os os.environ["CUDA_VISIBLE_DEVICES"]="0" a=tf.constant(2) b=tf.constant(3) with tf.compat.v1.Session() as sess: print("a:%i" % sess.run(a),"b:%i" % sess.run(b)) print("Addition with constants: %i" % sess.run(a+b)) print("Multiplication with constant:%i" % sess.run(a*b)) matrix1=tf.constant([[3.,3.]]) matrix2=tf.constant([[2.],[2.]]) product=tf.matmul(matrix1,matrix2) with tf.compat.v1.Session() as sess: result = sess.run(product) print(result)
运行结果:
a:2 b:3
Addition with constants: 5
Multiplication with constant:6
2.
import tensorflow.compat.v1 as tf tf.disable_v2_behavior() #使用变量Variable构造计算图a,b a=tf.placeholder(tf.int16) b=tf.placeholder(tf.int16) #使用tf中的add,multiply函数对a,b进行求和与求积操作 add=tf.add(a,b) mul=tf.multiply(a,b) #创建一个Session会话对象,调用run方法,运行计算图 with tf.Session() as sess: print("Addition with variables: %i" % sess.run(add,feed_dict={a:2,b:3})) print("Multiplication with variables: %i" %sess.run(mul,feed_dict={a:2,b:3}))
运行结果:
Addition with variables: 5
Multiplication with variables: 6
遇到问题:
由于python3X 与 python2x 有所变换 sess 无法使用
python3 引用:
import tensorflow as tf
tf.compat.v1.disable_eager_execution() #保证sess.run()能够正常运行
python2 直接引用:
import tensorflow as tf
保证
placeholder 函数能够调用
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()