placeholder（）

最新推荐文章于 2023-10-22 23:40:14 发布

丸子的牛

最新推荐文章于 2023-10-22 23:40:14 发布

阅读量304

点赞数

分类专栏： python

本文链接：https://blog.csdn.net/weixin_43890621/article/details/115495068

版权

python 专栏收录该内容

3 篇文章 0 订阅

订阅专栏

# coding = UTF-8

import tensorflow as tf
# placeholder理解为方法的形参，如要使用，必须传入参数
x1 = tf.placeholder(dtype = tf.float32, shape = None)
y1 = tf.placeholder(dtype = tf.float32, shape = None)
z1 = x1 + y1


x2 = tf.placeholder(dtype = tf.float32, shape = None)
y2 = tf.placeholder(dtype = tf.float32, shape = None)
z2 = tf.matmul(x2, y2)

with tf.Session() as sess:
传入参数
    z1_value = sess.run(z1, feed_dict = {x1:1, y1:2})
    z1_value, z2_value = sess.run(
        [z1, z2],
        feed_dict = {
            x1:1, y1:2,
            x2:[[2],
                [2]],
            y2:[[3, 3]]
                     }
    )
    print(z1_value)
    print(z2_value)