Tensorflow while_loop训练

Question

在我的问题，我需要运行GD与每个训练步骤的数据1例。这是已知的问题，session.run（）具有开销，因此训练模型的时间太长。 为了避免开销，我尝试使用while_loop并使用一次run（）调用来训练所有数据的模型。但它的方法不工作，train_op甚至不执行。下面是我在做什么的简单例子：

data = [k*1. for k in range(10)] 
tf.reset_default_graph() 

i = tf.Variable(0, name='loop_i') 
q_x = tf.FIFOQueue(100000, tf.float32) 
q_y = tf.FIFOQueue(100000, tf.float32) 

x = q_x.dequeue() 
y = q_y.dequeue() 
w = tf.Variable(0.) 
b = tf.Variable(0.) 
loss = (tf.add(tf.mul(x, w), b) - y)**2 

gs = tf.Variable(0) 

train_op = tf.train.GradientDescentOptimizer(0.05).minimize(loss, global_step=gs) 

s = tf.Session() 
s.run(tf.initialize_all_variables()) 

def cond(i): 
    return i < 10 

def body(i): 
    return tf.tuple([tf.add(i, 1)], control_inputs=[train_op]) 


loop = tf.while_loop(cond, body, [i]) 

for _ in range(1): 
    s.run(q_x.enqueue_many((data,))) 
    s.run(q_y.enqueue_many((data,))) 

s.run(loop) 
s.close() 

我在做什么错了？或者还有另外一个解决这个问题的开销太高的问题？

谢谢！

Answer 1

该模型不出现训练的原因是因为输入读数，梯度计算和minimize()呼叫都被定义外（且因此，在数据流而言，之前）的tf.while_loop()的主体。这意味着在循环执行之前，模型的所有这些部分只运行一次，而循环本身不起作用。

轻微重构—移动dequeue()操作，梯度计算，minimize()呼叫内环路—修复问题，并允许程序训练：

optimizer = tf.train.GradientDescentOptimizer(0.05) 

def cond(i): 
    return i < 10 

def body(i): 
    # Dequeue a new example each iteration. 
    x = q_x.dequeue() 
    y = q_y.dequeue() 

    # Compute the loss and gradient update based on the current example. 
    loss = (tf.add(tf.mul(x, w), b) - y)**2 
    train_op = optimizer.minimize(loss, global_step=gs) 

    # Ensure that the update is applied before continuing. 
    return tf.tuple([tf.add(i, 1)], control_inputs=[train_op]) 

loop = tf.while_loop(cond, body, [i]) 

---

UPDATE：这里有一个完成程序执行while循环，根据您的问题中的代码：

import tensorflow as tf 

# Define a single queue with two components to store the input data. 
q_data = tf.FIFOQueue(100000, [tf.float32, tf.float32]) 

# We will use these placeholders to enqueue input data. 
placeholder_x = tf.placeholder(tf.float32, shape=[None]) 
placeholder_y = tf.placeholder(tf.float32, shape=[None]) 
enqueue_data_op = q_data.enqueue_many([placeholder_x, placeholder_y]) 

gs = tf.Variable(0) 
w = tf.Variable(0.) 
b = tf.Variable(0.) 
optimizer = tf.train.GradientDescentOptimizer(0.05) 

# Construct the while loop. 
def cond(i): 
    return i < 10 

def body(i): 
    # Dequeue a single new example each iteration. 
    x, y = q_data.dequeue() 
    # Compute the loss and gradient update based on the current example. 
    loss = (tf.add(tf.multiply(x, w), b) - y) ** 2 
    train_op = optimizer.minimize(loss, global_step=gs) 
    # Ensure that the update is applied before continuing. 
    with tf.control_dependencies([train_op]): 
     return i + 1 

loop = tf.while_loop(cond, body, [tf.constant(0)]) 

data = [k * 1. for k in range(10)] 

with tf.Session() as sess: 
    sess.run(tf.global_variables_initializer()) 
    for _ in range(1): 
     # NOTE: Constructing the enqueue op ahead of time avoids adding 
     # (potentially many) copies of `data` to the graph. 
     sess.run(enqueue_data_op, 
       feed_dict={placeholder_x: data, placeholder_y: data}) 
    print (sess.run([gs, w, b])) # Prints before-loop values. 
    sess.run(loop) 
    print (sess.run([gs, w, b])) # Prints after-loop values.