TensorFlow 初级课程笔记 - 徐ShoweR

# TensorFlow 初级课程笔记

自己通过线性回归课程，然后边看边写的神经网络小例子

```python
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

# 使用numpy生成200个随机值
x_data = np.linspace(-0.5,0.5,200)[:,np.newaxis]
# 生成一些形状和x_data一样的干扰
noise = np.random.normal(0,0.02,x_data.shape)

y_data = np.square(x_data) + noise

# 定义两个placeholder
x = tf.placeholder(tf.float32,[None,1])
y = tf.placeholder(tf.float32,[None,1])

# 定义神经网络中间层
# 输入层1 中间层自己定义10个神经元
Weights_L1 = tf.Variable(tf.random_normal([1,10]))
biases_L1 = tf.Variable(tf.random_normal([1,10]))
Wx_plus_b_L1 = tf.matmul(x,Weights_L1) + biases_L1
L1 = tf.nn.tanh(Wx_plus_b_L1)

Weights_L2 = tf.Variable(tf.random_normal([10,1]))
biases_L2 = tf.Variable(tf.random_normal([1,1]))
Wx_plus_b_L2 = tf.matmul(L1,Weights_L2) + biases_L2
L2 = tf.nn.tanh(Wx_plus_b_L2)

# 代价函数
loss = tf.reduce_mean(tf.square(y - L2))
# 梯度下降法
optimizer = tf.train.GradientDescentOptimizer(0.2)
train = optimizer.minimize(loss)

init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    for _ in range(2000):
        sess.run(train,feed_dict={x:x_data,y:y_data})

prediction_value = sess.run(L2,feed_dict={x:x_data})

# 画图
    plt.figure()
    plt.scatter(x_data,y_data)
    plt.plot(x_data,prediction_value,'r-',lw = 5)
    plt.show()

```

但是有个小问题我不太清楚 就是把tanh函数全换成sigmoid以后就失效了 没想明白原因是什么