y = w*x+b
import tensorflow as tf
import numpy as np
#去掉警告信息
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
#create data
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data*0.1+0.3
# create tensorflow structure start
Weights = tf.Variable(tf.random_uniform([1],-1.0,1.0))
biases = tf.Variable(tf.zeros([1]))
y= Weights*x_data +biases
#计算平均误差
loss =tf.reduce_mean(tf.square(y-y_data))
#传播误差
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
#训练
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
for step in range(201):
sess.run(train)
if step %20 ==0:
print(step,sess.run(Weights),sess.run(biases))
拓展为二维
y = w1x1+w2x2+b
import tensorflow as tf
import numpy as np
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
#create data
x_data = np.random.rand(100).astype(np.float32)
x1_data = np.random.rand(100).astype(np.float32)
# y_data = x_data*0.1+0.3
y_data = 10*x_data + 20*x1_data + 100
# create tensorflow structure start
Weights = tf.Variable(tf.random_uniform([1],-1.0,1.0))
Weights1 = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
biases = tf.Variable(tf.zeros([1]))
y= Weights*x_data + Weights1 * x1_data+biases
#计算平均误差
loss =tf.reduce_mean(tf.square(y-y_data))
#传播误差
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
#训练
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
for step in range(201):
sess.run(train)
if step %20 ==0:
print(step,sess.run(Weights), sess.run(Weights1),sess.run(biases))
