9 查看图形化的模型

最新推荐文章于 2024-11-24 12:52:03 发布

转载最新推荐文章于 2024-11-24 12:52:03 发布 · 365 阅读

深度学习基于Python语言和TensorFlow平台专栏收录该内容

14 篇文章

订阅专栏

用TensorBoard查看数据流图

9.1 graph1
程序：

import tensorflow as tf

x = tf.placeholder(shape=[1, 3], dtype=tf.float32)

w = tf.Variable(tf.ones([3, 3]), dtype=tf.float32)
b = tf.Variable(1, dtype=tf.float32)

y = tf.matmul(x, w) + b

sess = tf.Session()
sess.run(tf.global_variables_initializer())

sess.run(y, feed_dict={x: [[1, 2, 3]]})

writer = tf.summary.FileWriter("graph", sess.graph)

cmd命令行输入：

tensorboard --logdir=E:\PycharmProjects\test20190712\graph

结果：
在这里插入图片描述
浏览器输入：

http://DESKTOP-6J6UU6I:6006/

控制TensorBoard图中对象的名称

7.2 graph2
程序：

import tensorflow as tf

x = tf.placeholder(shape=[1, 3], dtype=tf.float32, name="x")

w = tf.Variable(tf.ones([3, 3]), dtype=tf.float32, name="w")
b = tf.Variable(1, dtype=tf.float32, name="b")

y = tf.matmul(x, w, name="MatMul") + b

sess = tf.Session()
sess.run(tf.global_variables_initializer())

sess.run(y, feed_dict={x: [[1, 2, 3]]})

writer = tf.summary.FileWriter("graph", sess.graph)

结果：

9.3 graph3
程序：

import tensorflow as tf

x = tf.placeholder(shape=[1, 3], dtype=tf.float32, name="x")

w = tf.Variable(tf.ones([3, 3]), dtype=tf.float32, name="w")
b = tf.Variable(1, dtype=tf.float32, name="b")

y = tf.add(tf.matmul(x, w, name="MatMul"), b, name="y-Add")

sess = tf.Session()
sess.run(tf.global_variables_initializer())

sess.run(y, feed_dict={x: [[1, 2, 3]]})

writer = tf.summary.FileWriter("graph", sess.graph)

结果：