import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
# 使用numpy生成200个随机点
x_data = np.linspace(-0.5, 0.5, 200)[:,np.newaxis]
noise = np.random.normal(0, 0.02, x_data.shape)
y_data = np.square(x_data) + noise
# 定义两个placeholder,x,y为一维数组
x = tf.placeholder(tf.float32,[None, 1])
y = tf.placeholder(tf.float32,[None, 1])
# 定义神经网络的中间层
# 一个输入,10个神经元输出
Weights_L1 = tf.Variable(tf.random_normal([1, 10]))
biases_L1 = tf.Variable(tf.zeros([1,10]))
Wx_plus_b_L1 = tf.matmul(x,Weights_L1) + biases_L1
L1 = tf.nn.tanh(Wx_plus_b_L1)
# 输出层
# 10个神经元输入,一个输出
Weights_L2 = tf.Variable(tf.random_normal([10, 1]))
biases_L2 = tf.Variable(tf.zeros([1,1]))
Wx_plus_b_L2 = tf.matmul(L1,Weights_L2) + biases_L2
prediction = tf.nn.tanh(Wx_plus_b_L2)
# 二次函数代价
loss = tf.reduce_mean(tf.square(y-prediction))
# 使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(l
Tensorflow 一维回归练习
最新推荐文章于 2022-05-02 14:43:18 发布