在TensorFlow中,返回参数值有两种方法
- fetch
可以直接传入一些tensor来传回运行结果,在下面的例程中,input2和input3作为张量输入得到add_1
import tensorflow as tf
# fetch
input1 = tf.constant(3.0)
input2 = tf.constant(2.0)
input3 = tf.constant(5.0)
add_1 = tf.add(input2, input3)
mul = tf.multiply(input1, add_1)
with tf.Session() as sess:
result = sess.run([mul, add_1])
print(result)
- feed
在下面的例子中,feed是在sess会话中传入input1和input2参数值的,前提是需要声明input1和input2两个占位符。
import tensorflow as tf
input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
output = tf.multiply(input1, input2)
with tf.Session() as sess:
print(sess.run(output, feed_dict={input1: [7.0], input2: [2.0]}))