TF基本概念

来源:互联网 发布:产品经理 原型软件 编辑:程序博客网 时间:2024/05/22 00:11

TF基本概念

Graph 表示计算任务

Node 可以是Operation也可以是数据存储容器

在session的context中执行graph

使用tensor表示数据

通过variable维护状态

使用feed和fetch 为任意操作赋值(arbitrary operation)或者从中获取数据

Tensor 类似于numpy 中的数组

3# a rank 0 tensor; this is a scalar withshape [][1. ,2., 3.] # a rank 1tensor; this is a vector with shape [3][[1., 2., 3.], [4., 5., 6.]] # a rank 2tensor; a matrix with shape [2, 3][[[1., 2., 3.]], [[7., 8., 9.]]] # a rank 3tensor with shape [2, 1, 3]


Computational Graph包括两步

1、  Building the computational graph.

将TF操作转换成Graph nodes的形式,每个node包括input Tensor 和 output Tensor;constant node 只有固定输入没有输出

Eg:

import tensorflow as tfnode1 = tf.constant(3.0, tf.float32)node2 = tf.constant(4.0) # also tf.float32 implicitlyprint node1, node2

[out]

 

Tensor("Const:0", shape=TensorShape([]), dtype=float32)Tensor("Const_1:0", shape=TensorShape([]), dtype=float32)

sess = tf.Session()print sess.run([node1,node2])

 

[out]

[3.0, 4.0]

 

将上述两个node 相加产生新的node 并输出computation graph

node3 = tf.add(node1, node2)print "node3: ", node3print "sess.run(node3):",sess.run(node3)


[out]

node3: Tensor("Add:0", shape=TensorShape([]), dtype=float32)

sess.run(node3):  7.0

 

Placeholders可以不需要在定义的时候赋值,可以随后赋值

EG:

IN:

a = tf.placeholder(tf.float32)b = tf.placeholder(tf.float32)adder_node = a + b  # + provides a shortcut for tf.add(a, b) print sess.run(adder_node, {a: 3, b:4.5})print sess.run(adder_node, {a: [1,3], b:[2, 4]})


OUT:

7.5

[ 3. 7.]

 

在此基础上在加一个graph

IN:

add_add_triple = adder_node * 3.print sess.run(add_add_triple,{a:3,b:4.5})

OUT:

22.5

 

2、Running thecomputational graph.

为了计算node 值(3.0)(4.0)必须使用Session

 

 

Variables 可以将trainableparameters 加到graph中

构造Variable需要类型和初值

 

IN:

 

W = tf.Variable([.3], tf.float32)b = tf.Variable([-.3], tf.float32)x = tf.placeholder(tf.float32) linear_model = W * x +b

 

#variable initialize needs call a specialoperation

 

init = tf.initialize_all_variables() sess.run(init) print sess.run(linear_model,{x:[1,2,3,4]}) 

OUT:

[ 0.          0.30000001  0.60000002 0.90000004]

 

计算loss func

IN:

 

############ y and calculate loss function

y = tf.placeholder(tf.float32)squared_deltas = tf.square(linear_model -y)loss = tf.reduce_sum(squared_deltas) printsess.run(loss,{x:[1,2,3,5],y:[0,-1,-2,-3]})


OUT:

26.09

 

手动调参 tf.assign

####adjust the parametres by hand

 

IN:

fixW = tf.assign(W,[-1.])fixb = tf.assign(b,[1.])sess.run([fixW, fixb])printsess.run(loss,{x:[1,2,3,4],y:[0,-1,-2,-3]}) 

OUT:

0.0

 

自动调参数gradient decent

 

IN:

 

#gradientDescent optimeze the parameter

 

optimizer =tf.train.GradientDescentOptimizer(0.01)train = optimizer.minimize(loss) sess.run(init) for i in range(1000):   sess.run(train,{x:[1,2,3,4],y:[0,-1,-2,-3]}) print sess.run([W,b])


 

[array([-0.9999969], dtype=float32),array([ 0.99999082], dtype=float32)]

原创粉丝点击