搭建神经网络基本流程
- 训练的数据
- 定义节点准备接收数据
- 定义神经层:隐藏层和预测层
- 定义loss表达式
- 选择optimizer使loss达到最小
import tensorflow as tf
import numpy as np
# 训练的数据
x_data = np.linspace(-1, 1, 300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise
# 定义节点准备接收数据,也就是占位符
xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])
# 定义神经层:隐藏层和预测层
def add_layer(inputs, in_size, out_size, activation_function=None):
# add one more layer and return the output of this layer
Weights = tf.Variable(tf.random_normal([in_size, out_size]))
biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
Wx_plus_b = tf.matmul(inputs, Weights) + biases
if activation_function is None:
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b)
return outputs
# 输入值是xs, 隐藏层有10个神经元
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
# 输入值是隐藏层l1,预测层输出1个结果
prediction = add_layer(l1, 10, 1, activation_function=None)
# 定义loss表达式,以下采用平方差误差函数
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))
# 选择optimizer使loss达到最小,以下采用梯度下降法,学习率为0.1
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
# 对所有变量进行初始化
init = tf.global_variables_initializer()
sess = tf.Session()
# 上面定义的都没有运算,直到 sess.run 才会开始运算
sess.run(init)
# 迭代 1000 次学习,sess.run optimizer
for i in range(1000):
# training train_step 和 loss 都是由 placeholder 定义的运算,所以这里要用 feed 传入参数
sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
if i % 50 == 0:
# 每迭代50的倍数,打印损失值
print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))
从简短的代码中,看到TensorFlow的数据结构有:
- placeholder,主要用来喂数据
- Variable,定义一个变量,主要定义w和b
激励函数
dropout
dropout 是指在深度学习网络的训练过程中,按照一定的概率将一部分神经网络单元暂时从网络中丢弃,相当于从原始的网络中找到一个更瘦的网络。
代码实现就是在 add layer 函数里加上 dropout, keep_prob 就是保持多少不被 drop,在迭代时在 sess.run 中被 feed
def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):
# add one more layer and return the output of this layer
Weights = tf.Variable(tf.random_normal([in_size, out_size]))
biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, )
Wx_plus_b = tf.matmul(inputs, Weights) + biases
# here to dropout
# 在 Wx_plus_b 上drop掉一定比例
# keep_prob 保持多少不被drop,在迭代时在 sess.run 中 feed
Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)
if activation_function is None:
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b, )
tf.histogram_summary(layer_name + '/outputs', outputs)
return outputs
可视化Tensorboard
主要自动显示我们所建造的神经网络流程图,用 with tf.name_scope 定义各个框架,注意看代码注释中的区别:
import tensorflow as tf
def add_layer(inputs, in_size, out_size, activation_function=None):
# add one more layer and return the output of this layer
# 区别:大框架,定义层 layer,里面有 小部件
with tf.name_scope('layer'):
# 区别:小部件
with tf.name_scope('weights'):
Weights = tf.Variable(tf.random_normal([in_size, out_size]), name='W')
with tf.name_scope('biases'):
biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, name='b')
with tf.name_scope('Wx_plus_b'):
Wx_plus_b = tf.add(tf.matmul(inputs, Weights), biases)
if activation_function is None:
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b, )
return outputs
# 区别:大框架,里面有 inputs x,y
with tf.name_scope('inputs'):
xs = tf.placeholder(tf.float32, [None, 1], name='x_input')
ys = tf.placeholder(tf.float32, [None, 1], name='y_input')
# add hidden layer
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
# add output layer
prediction = add_layer(l1, 10, 1, activation_function=None)
# the error between prediciton and real data
# 区别:定义框架 loss
with tf.name_scope('loss'):
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),
reduction_indices=[1]))
# 区别:定义框架 train
with tf.name_scope('train'):
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
sess = tf.Session()
# 区别:sess.graph 把所有框架加载到一个文件中放到文件夹"logs/"里
# 接着打开terminal,进入你存放的文件夹地址上一层,运行命令 tensorboard --logdir='logs/'
# 会返回一个地址,然后用浏览器打开这个地址http://localhost:6006,在 graph 标签栏下打开
writer = tf.train.SummaryWriter("logs/", sess.graph)
# important step
sess.run(tf.global_variables_initializer())
保存和加载
训练好了一个神经网络后,可以保存起来下次使用时再次加载:
import tensorflow as tf
import numpy as np
## Save to file
# remember to define the same dtype and shape when restore
W = tf.Variable([[1,2,3],[3,4,5]], dtype=tf.float32, name='weights')
b = tf.Variable([[1,2,3]], dtype=tf.float32, name='biases')
init= tf.global_variables_initializer()
saver = tf.train.Saver()
# 用 saver 将所有的 variable 保存到定义的路径
with tf.Session() as sess:
sess.run(init)
save_path = saver.save(sess, "my_net/save_net.ckpt")
print("Save to path: ", save_path)
##############################################################################################
# 注意:这两段分开执行,第一步保存变量执行完,再执行加载变量,不然会报错。
# restore variables
# redefine the same shape and same type for your variables
W = tf.Variable(np.arange(6).reshape((2, 3)), dtype=tf.float32, name="weights")
b = tf.Variable(np.arange(3).reshape((1, 3)), dtype=tf.float32, name="biases")
# not need init step
saver = tf.train.Saver()
# 用 saver 从路径中将 save_net.ckpt 保存的 W 和 b restore 进来
with tf.Session() as sess:
saver.restore(sess, "my_net/save_net.ckpt")
print("weights:", sess.run(W))
print("biases:", sess.run(b))
tensorflow 现在只能保存 variables,还不能保存整个神经网络的框架,所以再使用的时候,需要重新定义框架,然后把 variables 放进去学习。
参考具体博客地址:https://www.jianshu.com/p/e112012a4b2d