我与深度学习 - [Tensorflow] - [最简单的神经网络]

一个入门的简单的训练

x_data = np.random.rand(100)
y_data = x_data * 0.1 + 0.2
b = tf.Variable(0.)
k = tf.Variable(0.)
y = x_data * k + b
loss = tf.reduce_mean(tf.square(y - y_data))
optimizer = tf.train.GradientDescentOptimizer(0.2)
train = optimizer.minimize(loss)
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    print(los)
    for step in range(201):
        sess.run(train)
        if step % 20 == 0:
            print(step, sess.run([k, b]))

 

 一个简单的神经网络做线性回归

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

x_data = np.linspace(-0.5, 0.5, 200)[:, np.newaxis]
print(x_data.shape)
noise = np.random.normal(0, 0.02, x_data.shape)
print(noise.shape)
y_data = np.square(x_data) + noise
x = tf.placeholder(tf.float32, [None, 1])
y = tf.placeholder(tf.float32, [None, 1])


weigthts_l1 = tf.Variable(tf.random_normal([1, 10]))
biases_l1 = tf.Variable(tf.zeros([1, 10]))
wx_plus_b_l1 = tf.matmul(x, weigthts_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.zeros([1, 1]))
wx_plus_b_l2 = tf.matmul(l1, weights_l2) + biases_l2
prediction = tf.nn.tanh(wx_plus_b_l2)

loss = tf.reduce_mean(tf.square(prediction - y))
optimizer = tf.train.GradientDescentOptimizer(0.1)
train = optimizer.minimize(loss)


with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for _ in range(2000):
        sess.run(train, feed_dict = {x:x_data, y:y_data})
    l1_value = sess.run(wx_plus_b_l1, feed_dict = {x:x_data})
    print(l1_value)
    prediction_value = sess.run(prediction, feed_dict = {x:x_data})
    plt.figure()
    plt.scatter(x_data, y_data)
    plt.plot(x_data, prediction_value, 'r-', lw=5)
    plt.show()