TensorFlow-step1

import tensorflow as tf
node1 = tf.constant(3.0, tf.float32) #数值不变
print(node1)
node2 = tf.constant(4.0)
print(node2)
print(node1,node2)
sess = tf.Session()
print(sess.run([node1, node2]))    #调用run方法显示
node3 = tf.add(node1, node2)
print(node3)
print(sess.run(node3))
W = tf.Variable([.3], tf.float32)    #值可变，赋初值
b = tf.Variable([.3], tf.float32)
x = tf.placeholder(tf.float32)      #占位符
linear_model = W * x + b           
print(sess.run(linear_model, {x:[1,2,3,4]}))
init = tf.global_variables_initializer()
sess.run(init)
print(sess.run(linear_model, {x:[1,2,3,4]}))
W = tf.Variable([.3], tf.float32)
b = tf.Variable([-.3], tf.float32)
x = tf.placeholder(tf.float32)
linear_model = W * x + b
init = tf.global_variables_initializer()
sess.run(init)        #初始化
print(sess.run(linear_model, {x:[1,2,3,4]}))
print(sess.run(linear_model, {x:[1,2,3,4,5]}))
print(sess.run(linear_model, {x:[1,2,3,4,5,6]}))
y = tf.placeholder(tf.float32)
squared_deltas = tf.square(linear_model -y ) #标准损失sum（x-y）^2
loss = tf.reduce_sum(squared_deltas)
print(sess.run(loss, {x:[1,2,3,4], y:[0,-1,-2,-3]}))
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]}))
optimizer = tf.train.GradientDescentOptimizer(0.01) #梯度下降
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]))