一个简单的神经网络

这是一个简单的神经网络

import tensorflow as tf

from numpy.random import RandomState

batch_size = 8

w1 = tf.Variable(tf.random_normal([2,3],stddev=1,seed=1))
w2 = tf.Variable(tf.random_normal([2,3],stddev=1,seed=1))

x = tf.placeholder(tf.float32, shape=(None,2), name='xinput')
y = tf.placeholder(tf.float32, shape=(None,2), name='yinput')

a = tf.matmul(x,w1)
b = tf.matmul(y,w2)

cross_entropy = -tf.reduce_mean(y*tf.log(tf.clip_by_value(y, 1e-10, 1.0)))
train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy)

rdm = RandomState(1)
dataset_size = 128
X = rdm.rand(dataset_size, 2)
Y = [[int(x1+x2 < 1)] for (x1, x2) in X]

with tf.Session() as sess:
    init_op = tf.initialize_all_variables()
    sess.run(init_op)
    print sess.run(w1)
    print sess.run(w2)

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_crossentropy = sess.run(cross_entropy, feed_dict={x:X, y:Y})

总结下来神经网络训练过程分为一下三个步骤
1.定义神经网络的结构和前向传播的输出结果
2.定义损失函数以及选择反向传播优化的算法
3.生成绘画（tf.Session）并且在训练数据上反复运行反向传播优化算法。