tensorflow的核心数据单元是tensor，它的rank表示数据的维度。

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

导入tensorflow

import tensorflow as tf

计算图

我们可以简单的认为，tensorflow core程序大致分为两个部分：构建计算图和运行计算图。

常量运算

创建常量tensor

node1 = tf.constant(3.0, dtype=tf.float32)
node2 = tf.constant(4.0) # also tf.float32 implicitly
print(node1, node2)

运行上面的常量

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

简单的加法运算

from __future__ import print_function
node3 = tf.add(node1, node2)
print("node3:", node3)
print("sess.run(node3):", sess.run(node3))

接收外部输入

a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
adder_node = a + b  # + provides a shortcut for tf.add(a, b)

计算输入值

print(sess.run(adder_node, {a: 3, b: 4.5}))
print(sess.run(adder_node, {a: [1, 3], b: [2, 4]}))

乘法运算

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

创建模型

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

初始化变量

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

运行模型

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

评估模型

计算模型损失函数(方差)

y = tf.placeholder(tf.float32)
squared_deltas = tf.square(linear_model - y)
loss = tf.reduce_sum(squared_deltas)
print(sess.run(loss, {x: [1, 2, 3, 4], y: [0, -1, -2, -3]}))

修改模型参数

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