Question

为了训练模型，我将我的模型封装在一个类中。我使用tf.RandomShuffleQueue将文件名列表排入队列。但是，当我将元素出列队列时，它们会出列但队列的大小不会减少。

以下是代码段后面的更具体的问题：

例如，如果我只有5张图片，但步数范围高达100，这是否会导致addfilenames自动重复调用？它没有给我任何关于出队的错误，所以我认为它会被自动调用。

为什么tf.RandomShuffleQueue的大小没有变化？它保持不变。

import os
import time
import functools
import tensorflow as tf
from Read_labelclsloc import readlabel


def ReadTrain(traindir):
    # Returns a list of training images, their labels and a dictionay.
    # The dictionary maps label names to integer numbers.                                                                    
    return trainimgs, trainlbls, classdict


def ReadVal(valdir, classdict):
   # Reads the validation image labels.
   # Returns a dictionary with filenames as keys and 
   # corresponding labels as values.
    return valdict

def lazy_property(function):
  # Just a decorator to make sure that on repeated calls to 
  # member functions, ops don't get created repeatedly.
  # Acknowledgements : https://danijar.com/structuring-your-tensorflow-models/
    attribute= '_cache_' + function.__name__
    @property
    @functools.wraps(function)
    def decorator(self):
        if not hasattr(self, attribute):
            setattr(self, attribute, function(self))
        return getattr(self, attribute)

    return decorator    

class ModelInitial:

    def __init__(self, traindir, valdir):
        self.graph
        self.traindir = traindir
        self.valdir = valdir
        self.traininginfo()
        self.epoch = 0



    def traininginfo(self):
        self.trainimgs, self.trainlbls, self.classdict = ReadTrain(self.traindir)
        self.valdict = ReadVal(self.valdir, self.classdict)
        with self.graph.as_default():
            self.trainimgs_tensor = tf.constant(self.trainimgs)
            self.trainlbls_tensor = tf.constant(self.trainlbls, dtype=tf.uint16)
            self.trainimgs_dict = {}
            self.trainimgs_dict["ImageFile"] = self.trainimgs_tensor
        return None

    @lazy_property
    def graph(self):
        g = tf.Graph()
        with g.as_default():
           # Layer definitions go here 
        return g


    @lazy_property
    def addfilenames (self):
   # This is the function where filenames are pushed to a RandomShuffleQueue
        filename_queue = tf.RandomShuffleQueue(capacity=len(self.trainimgs), min_after_dequeue=0,\
                                               dtypes=[tf.string], names=["ImageFile"],\
                                               seed=0, name="filename_queue")

        sz_op = filename_queue.size()

        dq_op = filename_queue.dequeue()

        enq_op = filename_queue.enqueue_many(self.trainimgs_dict)
        return filename_queue, enq_op, sz_op, dq_op

    def Train(self):
    # The function for training.
    # I have not written the training part yet.
    # Still struggling with preprocessing 
        with self.graph.as_default():
            filename_q, filename_enqueue_op, sz_op, dq_op= self.addfilenames

            qr = tf.train.QueueRunner(filename_q, [filename_enqueue_op])
            filename_dequeue_op = filename_q.dequeue()
            init_op = tf.global_variables_initializer()

        sess = tf.Session(graph=self.graph)
        sess.run(init_op)
        coord = tf.train.Coordinator()
        enq_threads = qr.create_threads(sess, coord=coord, start=True)
        counter = 0
        for step in range(100):
            print(sess.run(dq_op["ImageFile"]))
            print("Epoch = %d "%(self.epoch))
            print("size = %d"%(sess.run(sz_op)))
            counter+=1

        names = [n.name for n in self.graph.as_graph_def().node]
        coord.request_stop()
        coord.join(enq_threads)
        print("Counter = %d"%(counter))
        return None





if __name__ == "__main__":
    modeltrain = ModelInitial(<Path to training images>,\
                                    <Path to validation images>)
    a = modeltrain.graph
    print(a)
    modeltrain.Train()
    print("Success")

Answer 1

这个谜是由您为队列创建的this引起的，这会导致它在后台填充。

以下行导致创建后台“queue runner”线程：
```
qr = tf.train.QueueRunner(filename_q, [filename_enqueue_op])
# ... 
enq_threads = qr.create_threads(sess, coord=coord, start=True)
```
此线程在循环中调用filename_enqueue_op，这会导致在从中删除元素时填充队列。
步骤1中的后台线程几乎总是在队列上有一个挂起的入队操作（filename_enqueue_op）。这意味着在您使文件名出列后，挂起的enqueue将运行add，将队列填充回容量。（从技术上讲，这里存在竞争条件，您可以看到capacity - 1的大小，但这是不太可能的。）

从RandomShuffleQueue出队不会减小尺寸

1 个答案: