variable
来源:互联网 发布:linux用户加入组 编辑:程序博客网 时间:2024/05/17 07:53
变量Variable
变量用于存储和更新参数,是内存中用于存放张量(Tensor)的缓存区,必须明确的初始化,并能在训练过程种和结束后保存到磁盘.
* 创建
需要传入一个初始和shape
你将一个 张量 作为初始值传入 Variable() 构造函数。TensorFlow提供了一系列操作符来初始化张量,初始值是常量或是随机值
import tensorflow as tf# Create a variable.w = tf.Variable(<initial-value>, name=<optional-name>)weights = tf. Variable(tf. random_normal([784, 200] , stddev=0.35) ,name="weights")biases = tf. Variable(tf. zeros([200] ) , name="biases")
* 调用 tf.Variable() 添加一些操作(Op, operation)到graph:
# Use the variable in the graph like any Tensor. y = tf.matmul(w, ...another variable or tensor...) # The overloaded operators are available too. z = tf.sigmoid(w + b)
- 给w赋新值
# Assign a new value to the variable with `assign()` or a related method. w.assign(w + 1.0) w.assign_add(1.0)
初始化
# Create two variables.创建两个变量 weights = tf. Variable(tf. random_normal([784, 200] , stddev=0.35) , name="weights") biases = tf. Variable(tf. zeros([200] ) , name="biases") # Add an Op to initialize all variables.添加一个节点用来初始化变量 init_op = tf.initialize_all_variables() # Later, when launching the model 运行模型 with tf. Session() as sess: # Run the init operation. sess. run(init_op) ... # Use the model
由另一个变量初始化
# Create a variable with a random value.weights = tf. Variable(tf. random_normal([784, 200] , stddev=0.35) ,name="weights")# Create another variable with the same value as 'weights'.w2 = tf. Variable(weights. initialized_value() , name="w2")# Create another variable with twice the value of 'weights'w_twice = tf. Variable(weights. initialized_value() * 0.2, name="w_twice")
保存和加载
保存 tf.train.saver
# Create some variables.v1 = tf. Variable(... , name="v1")v2 = tf. Variable(... , name="v2")...# Add an op to initialize the variables.init_op = tf. initialize_all_variables()# Add ops to save and restore all the variables.saver = tf. train. Saver()# Later, launch the model, initialize the variables, do some work, save the# variables to disk.with tf. Session() as sess:sess. run(init_op)# Do some work with the model...# Save the variables to disk.保存变量至检查点save_path = saver. save(sess, "/tmp/model.ckpt")print "Model saved in file: ", save_path
恢复变量
用同一个 Saver 对象来恢复变量。注意,当你从文件中恢复变量时,不需要事先对它们做初始化。
save.restore# Create some variables.v1 = tf. Variable(... , name="v1")v2 = tf. Variable(... , name="v2")...# Add ops to save and restore all the variables.saver = tf. train. Saver()# Later, launch the model, use the saver to restore variables from disk, and# do some work with the model.with tf. Session() as sess:# Restore variables from disk.saver. restore(sess, "/tmp/model.ckpt")print "Model restored."# Do some work with the model...
恢复部分变量
# Create some variables.v1 = tf. Variable(... , name="v1")v2 = tf. Variable(... , name="v2")...# Add ops to save and restore only 'v2' using the name "my_v2"saver = tf. train. Saver({"my_v2": v2} )# Use the saver object normally after that.
0 0
- Variable
- Variable
- variable
- variable
- 关于shell中$VARIABLE ${VARIABLE} "$VARIABLE"
- Class Variable
- Instance Variable
- Shell - Variable
- shell Variable
- variable argument
- linux Variable
- $(origin <variable>;)
- signal variable
- static variable,
- Unuser Variable‘ ’
- Python Variable
- Final variable
- Static Variable
- Git 的origin和master分析
- mybatis事务传播行为
- 从零开始学Makefile(七)
- css
- iOS 中对IPv6的适配
- variable
- Apache Thrift 官方JAVA教程
- js判断是否在微信浏览器中打开
- 复制转发CSDN博客快捷方法
- java selenium (八) Selenium IDE 用法
- Jquery ajax 提交表单
- HashMap源码分析(基于jdk1.6)
- 算法导论 练习题 10.4-2
- 使用BigDecimal进行精确运算