1.利用TensorFlow实现一个简单的例子;
2.重点的知识有:定义权重和输入输出的placeholder;前向传播;反向传播;优化;损失函数;batch_size的基本概念
3.总结起来,训练过程可分为三个步骤:
1.定义神经网络的结构和前向传播;
2.定义损失函数,选择优化算法
3.生成会话,选择batch_size迭代;
import tensorflow as tf
from numpy.random import RandomState #通过numpy生成模拟数据集
#定义batch的大小
batch_size = 8
#定义神经网络的参数;
w1 = tf.Variable(tf.random_normal([2, 3], stddev=1, seed=1))
w2 = tf.Variable(tf.random_normal([3, 1], stddev=1, seed=1))
x = tf.placeholder(tf.float32, shape=(None, 2), name="x-input")
y_ = tf.placeholder(tf.float32, shape=(None, 1), name="y-input")
#定义前向传播;
a = tf.matmul(x, w1)
y = tf.matmul(a, w2)
#定义损失函数(交叉熵)和反向传播的算法;
y = tf.sigmoid(y)
cross_entropy = -tf.reduce_mean(
y_ * tf.log(tf.clip_by_value(y, 1e-10, 1.0))
+ (1-y_)*tf.log(tf.clip_by_value(1-y, 1e-10, 1.0)))
train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy)
#生成一个模拟数据集;
rdm = RandomState(1)
dataset_size = 128
X = rdm.rand(dataset_size, 2)
Y = [[int(x1+x2 < 1)] for (x1, x2) in X]
#创建一个会话运行程序;
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
print(sess.run(w1))
print(sess.run(w2))
#设置迭代次数;
steps = 5000
for i in range(steps):
start = (i * batch_size) % dataset_size
end = min(start+batch_size, dataset_size)
sess.run(train_step,
feed_dict={x: X[start:end], y_: Y[start:end]})
if i % 1000 == 0:
total_cross_entropy = sess.run(
cross_entropy, feed_dict={x:X, y_:Y})
print(i, total_cross_entropy)
print(sess.run(w1))
print(sess.run(w2))
输出结果如下:
[[-0.8113182 1.4845988 0.06532937]
[-2.4427042 0.0992484 0.5912243 ]]
[[-0.8113182 ]
[ 1.4845988 ]
[ 0.06532937]]
0 0.77943563
1000 0.7338941
2000 0.73070776
3000 0.73061645
4000 0.7305646
[[-0.427144 0.251661 1.6811208]
[-1.8636073 -0.7442908 1.7735264]]
[[ 0.1367231]
[ 0.5396503]
[-1.3507011]]