Tensorflow 实战Google深度学习框架 Python3 代码

原书名《Tensorflow 实战Google深度学习框架》

由于自己用的是python 3,而且书中所使用的部分方法已经更改，所以自己对原书的代码进行了些许修改，并成功在Jupyter上运行成功。

88-89页 损失函数计算：换掉lambda

import tensorflow as tf

def get_weight(shape,lamba):
var=tf.Variable(tf.random_normal(shape),dtype=tf.float32)
tf.add_to_collection('losses',tf.contrib.layers.l2_regularizer(0.5)(var))
return var

#生成样本集
x=tf.placeholder(tf.float32,shape=(None,2))
y_=tf.placeholder(tf.float32,shape=(None,2))
batch_size=8

#生成层数与节点数
layer_dimension=[2,10,10,10,1]
n_layers=len(layer_dimension)

cur_layer=x
in_dimension=layer_dimension[0]

for i in range(1,n_layers):
out_dimension=layer_dimension[i]
weight=get_weight([in_dimension,out_dimension],0.001)
bias=tf.Variable(tf.constant(0.1,shape=[out_dimension]))
cur_layer=tf.nn.relu(tf.matmul(cur_layer,weight)+bias)
in_dimension=layer_dimension[i]

mse_loss=tf.reduce_mean(tf.square(y_-cur_layer))

tf.add_to_collection('losses',mse_loss)

loss=tf.add_n(tf.get_collection('losses'))

90-91 平滑损失函数
import tensorflow as tf

v1=tf.Variable(0,dtype=tf.float32)
step=tf.Variable(0,trainable=False)

ema=tf.train.ExponentialMovingAverage(0.99,step)

maintain_averages_op=ema.apply([v1])

with tf.Session() as sess:
init_op=tf.global_variables_initializer()
sess.run(init_op)

print(sess.run([v1,ema.average(v1)]))

sess.run(tf.assign(v1,5))
sess.run(maintain_averages_op)
print(sess.run([v1,ema.average(v1)]))

sess.run(tf.assign(step,10000))
sess.run(tf.assign(v1,10))
sess.run(maintain_averages_op)
print(sess.run([v1,ema.average(v1)]))

sess.run(maintain_averages_op)
print(sess.run([v1,ema.average(v1)]))