tensorflow 选择参数进行训练的方法

1 一般的训练过程

train的过程其实就是修改计算图中的tf.Variable的过程。

import tensorflow as tf
 
label = tf.constant(1,dtype = tf.float32)
prediction_to_train = tf.Variable(3,dtype=tf.float32)  # 指定了待训练的变量（参数）
manual_compute_loss = tf.square(prediction_to_train - label)  # 指定损失函数为待训练参数与常量1的平方

optimizer = tf.train.GradientDescentOptimizer(0.01)  # 选择优化器和对应的参数
train_step = optimizer.minimize(manual_compute_loss)  # 使用梯度下降优化损失函数
 
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for _ in range(10):
        print('variable is ', sess.run(prediction_to_train), ' and the loss is ',sess.run(manual_compute_loss))
        sess.run(train_step)

variable is  3.0  and the loss is  4.0
variable is  2.96  and the loss is  3.8416002
variable is  2.9208  and the loss is  3.6894724
variable is  2.882384  and the loss is  3.5433698
variable is  2.8447363  and the loss is  3.403052
variable is  2.8078415  and the loss is  3.268291
 
。。。。。。。
。。。
variable is  2.0062745  and the loss is  1.0125883
variable is  1.986149  and the loss is  0.9724898
variable is  1.966426  and the loss is  0.9339792
 
。。。。
。。。
 
variable is  1.0000029  and the loss is  8.185452e-12
variable is  1.0000029  and the loss is  8.185452e-12
variable is  1.0000029  and the loss is  8.185452e-12
variable is  1.0000029  and the loss is  8.185452e-12
variable is  1.0000029  and the loss is  8.185452e-12

2 限定训练的变量

根据train是修改计算图中tf.Variable（默认是计算图中所有tf.Variable，可以通过var_list指定）的事实，可以使用tf.constant或者python变量的形式来规避常量被训练，这也是迁移学习要用到的技巧。

label = tf.constant(1,dtype = tf.float32)  # 标签
x = tf.placeholder(dtype = tf.float32)
w1 = tf.Variable(4,dtype=tf.float32)  # 待训练参数1
w2 = tf.Variable(4,dtype=tf.float32)  # 待训练参数2
w3 = tf.constant(4,dtype=tf.float32)  # 常量权值
y_predict = w1*x+w2*x+w3*x  # 函数的输出
 
make_up_loss = tf.square(y_predict - label)
optimizer = tf.train.GradientDescentOptimizer(0.01)
train_step = optimizer.minimize(make_up_loss)
 
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for _ in range(2):
        w1_,w2_,w3_,loss_ = sess.run([w1,w2,w3,make_up_loss],feed_dict={x:1})
        print('variable is w1:',w1_,' w2:',w2_,' w3:',w3_, ' and the loss is ',loss_)
        sess.run(train_step,{x:1})

variable is w1: -1.4999986  w2: -1.4999986  w3: 4.0  and the loss is  8.185452e-12
variable is w1: -1.4999986  w2: -1.4999986  w3: 4.0  and the loss is  8.185452e-12

3 使用var_list指定训练变量

label = tf.constant(1,dtype = tf.float32)
x = tf.placeholder(dtype = tf.float32)
w1 = tf.Variable(4,dtype=tf.float32)
w2 = tf.Variable(4,dtype=tf.float32)
w3 = tf.constant(4,dtype=tf.float32)
 
y_predict = w1*x+w2*x+w3*x
 
#define losses and train
make_up_loss = tf.square(y_predict - label)
optimizer = tf.train.GradientDescentOptimizer(0.01)
train_step = optimizer.minimize(make_up_loss,var_list = w2)  # 指定待训练的变量为w2
 
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    for _ in range(7):
        w1_,w2_,w3_,loss_ = sess.run([w1,w2,w3,make_up_loss],feed_dict={x:1})
        print('variable is w1:',w1_,' w2:',w2_,' w3:',w3_, ' and the loss is ',loss_)
        sess.run(train_step,{x:1})

variable is w1: 4.0  w2: -6.99948  w3: 4.0  and the loss is  2.7063857e-07
variable is w1: 4.0  w2: -6.9994903  w3: 4.0  and the loss is  2.5983377e-07
variable is w1: 4.0  w2: -6.9995003  w3: 4.0  and the loss is  2.4972542e-07
variable is w1: 4.0  w2: -6.9995103  w3: 4.0  and the loss is  2.398176e-07
variable is w1: 4.0  w2: -6.9995203  w3: 4.0  and the loss is  2.3011035e-07
variable is w1: 4.0  w2: -6.99953  w3: 4.0  and the loss is  2.2105178e-07
variable is w1: 4.0  w2: -6.9995394  w3: 4.0  and the loss is  2.1217511e-07

若无可训练的 tf.Variable 变量，则会报错：

ValueError: No variables to optimize.

用var_list指定一个 tf.constant 常量，也无法实现：

NotImplementedError: ('Trying to update a Tensor ', )

4 使用tf.getCollection

label = tf.constant(1,dtype = tf.float32)
x = tf.placeholder(dtype = tf.float32)
w1 = tf.Variable(4,dtype=tf.float32)

with tf.name_scope(name='selected_variable_to_trian'):
    w2 = tf.Variable(4,dtype=tf.float32)
   
w3 = tf.constant(4,dtype=tf.float32)
y_predict = w1*x+w2*x+w3*x
 
make_up_loss = (y_predict - label)**3
optimizer = tf.train.GradientDescentOptimizer(0.01)
 
output_vars = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope='selected_variable_to_trian')  # 指定训练的变量域
train_step = optimizer.minimize(make_up_loss,var_list = output_vars)
 
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    for _ in range(3000):
        w1_,w2_,w3_,loss_ = sess.run([w1,w2,w3,make_up_loss],feed_dict={x:1})
        print('variable is w1:',w1_,' w2:',w2_,' w3:',w3_, ' and the loss is ',loss_)
        sess.run(train_step,{x:1})

variable is w1: 4.0  w2: -6.988893  w3: 4.0  and the loss is  1.3702081e-06
variable is w1: 4.0  w2: -6.988897  w3: 4.0  and the loss is  1.3687968e-06
variable is w1: 4.0  w2: -6.9889007  w3: 4.0  and the loss is  1.3673865e-06
variable is w1: 4.0  w2: -6.9889045  w3: 4.0  and the loss is  1.3659771e-06
variable is w1: 4.0  w2: -6.9889083  w3: 4.0  and the loss is  1.3645688e-06
variable is w1: 4.0  w2: -6.988912  w3: 4.0  and the loss is  1.3631613e-06
variable is w1: 4.0  w2: -6.988916  w3: 4.0  and the loss is  1.3617548e-06
variable is w1: 4.0  w2: -6.9889197  w3: 4.0  and the loss is  1.3603493e-06

转自：https://mp.csdn.net/mdeditor/97611750