import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
tf.set_random_seed(1)
np.random.seed(1)
x = np.linspace(-1, 1, 100)[:, np.newaxis] # shape (100, 1)
# 生成高斯分布的概率密度随机数
noise = np.random.normal(0, 0.1, size=x.shape)
# numpy.power() 函数将第一个输入数组中的元素作为底数,计算它与第二个输入数组中相应元素的幂
y = np.power(x, 2) + noise
plt.scatter(x, y)
plt.show()
tf_x = tf.placeholder(tf.float32, x.shape) # input x
tf_y = tf.placeholder(tf.float32, y.shape) # input y
# neural network layers
# dense :全连接层 相当于添加一个层
# tf.layers.dense(
#
# inputs,
#
# units,
#
# activation=None,
#
# use_bias=True,
#
# kernel_initializer=None, ##卷积核的初始化器
#
# bias_initializer=tf.zeros_initializer(), ##偏置项的初始化器,默认初始化为0
#
# kernel_regularizer=None, ##卷积核的正则化,可选
#
# bias_regularizer=None, ##偏置项的正则化,可选
#
# activity_regularizer=None, ##输出的正则化函数
#
# kernel_constraint=None,
#
# bias_constraint=None,
#
# trainable=True,
#
# name=None, ##层的名字
#
# reuse=None ##是否重复使用参数
#
# )
# 部分参数解释:
#
# inputs:输入该网络层的数据
#
# units:输出的维度大小,改变inputs的最后一维
#
# activation:激活函数,即神经网络的非线性变化
#
# use_bias:使用bias为True(默认使用),不用bias改成False即可,是否使用偏置项
l1 = tf.layers.dense(tf_x, 10, tf.nn.relu) # hidden layer
output = tf.layers.dense(l1, 1) # output layer
# tf.losses.mean_squared_error(labels:真实的输出张量,与“predictions”相同 , predictions:预测的输出)
loss = tf.losses.mean_squared_error(tf_y, output) # compute cost
# 梯度下降优化,最小化损失
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.5)
train_op = optimizer.minimize(loss)
sess = tf.Session() # control training and others
sess.run(tf.global_variables_initializer()) # initialize var in graph
plt.ion() # something about plotting
for step in range(100):
# train and net output
_, l, pred = sess.run([train_op, loss, output], {tf_x: x, tf_y: y})
if step % 5 == 0:
# plot and show learning process
plt.cla()
plt.scatter(x, y)
plt.plot(x, pred, 'r-', lw=5)
plt.text(0.5, 0, 'Loss=%.4f' % l, fontdict={'size': 20, 'color': 'red'})
plt.pause(0.1)
plt.ioff()
plt.show()
网友评论