在TensorFlow中进行模型训练时,在官网给出的三种读取方式,中最好的文件读取方式就是将利用队列进行文件读取,而且步骤有两步: 1. 把样本数据写入TFRecords二进制文件 2. 从队列中读取数据
使用队列读取数TFRecords 文件 数据的步骤 1. 创建张量,从二进制文件读取一个样本数据 2. 创建张量,从二进制文件随机读取一个mini-batch 3. 把每一批张量传入网络作为输入点
tensorflow-master\tensorflow\examples\how_tos\reading_data\fully_connected_reader.py(1.2.1)
解析主要在注释中,最后一个模块if __name__ == '__main__':的运行,建议参考’http://blog.csdn.net/fontthrone/article/details/76735591’
import tensorflow as tf import os # from tensorflow.contrib.learn.python.learn.datasets import mnist # 注意上面的这个mnist 与 example 中的 mnist 是不同的,本文件中请使用下面的那个 mnist os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' import argparse import os.path import sys import time from tensorflow.examples.tutorials.mnist import mnist # Basic model parameters as external flags. FLAGS = None # This part of the code is added by FontTian,which comes from the source code of tensorflow.examples.tutorials.mnist # The MNIST images are always 28x28 pixels. # IMAGE_SIZE = 28 # IMAGE_PIXELS = IMAGE_SIZE * IMAGE_SIZE # Constants used for dealing with the files, matches convert_to_records. TRAIN_FILE = 'train.tfrecords' VALIDATION_FILE = 'validation.tfrecords' def read_and_decode(filename_queue): reader = tf.TFRecordReader() _, serialized_example = reader.read(filename_queue) features = tf.parse_single_example( serialized_example, # Defaults are not specified since both keys are required. # 必须写明faetures 中的 key 的名称 features={ 'image_raw': tf.FixedLenFeature([], tf.string), 'label': tf.FixedLenFeature([], tf.int64), }) # Convert from a scalar string tensor (whose single string has # length mnist.IMAGE_PIXELS) to a uint8 tensor with shape # [mnist.IMAGE_PIXELS]. # 将一个标量字符串张量(其单个字符串的长度是mnist.image像素) # 0 维的Tensor # 转换为一个带有形状mnist.图像像素的uint8张量。 # 一维的Tensor image = tf.decode_raw(features['image_raw'], tf.uint8) # print(tf.shape(image)) # Tensor("input/Shape:0", shape=(1,), dtype=int32) image.set_shape([mnist.IMAGE_PIXELS]) # print(tf.shape(image)) # Tensor("input/Shape_1:0", shape=(1,), dtype=int32) # OPTIONAL: Could reshape into a 28x28 image and apply distortions # here. Since we are not applying any distortions in this # example, and the next step expects the image to be flattened # into a vector, we don't bother. # Convert from [0, 255] -> [-0.5, 0.5] floats. image = tf.cast(image, tf.float32) * (1. / 255) - 0.5 # print(tf.shape(image)) # Tensor("input/Shape_2:0", shape=(1,), dtype=int32) # Convert label from a scalar uint8 tensor to an int32 scalar. label = tf.cast(features['label'], tf.int32) # print(tf.shape(label)) # Tensor("input/Shape_3:0", shape=(0,), dtype=int32) return image, label # 使用 tf.train.shuffle_batch 将前面生成的样本随机化,获得一个最小批次的张量 def inputs(train, batch_size, num_epochs): """Reads input data num_epochs times. Args: train: Selects between the training (True) and validation (False) data. batch_size: Number of examples per returned batch. num_epochs: Number of times to read the input data, or 0/None to train forever. Returns: A tuple (images, labels), where: * images is a float tensor with shape [batch_size, mnist.IMAGE_PIXELS] in the range [-0.5, 0.5]. * labels is an int32 tensor with shape [batch_size] with the true label, a number in the range [0, mnist.NUM_CLASSES). Note that an tf.train.QueueRunner is added to the graph, which must be run using e.g. tf.train.start_queue_runners(). 输入参数: train: Selects between the training (True) and validation (False) data. batch_size: 训练的每一批有多少个样本 num_epochs: 读取输入数据的次数, or 0/None 表示永远训练下去 返回结果: A tuple (images, labels), where: * images is a float tensor with shape [batch_size, mnist.IMAGE_PIXELS] 范围: [-0.5, 0.5]. * labels is an int32 tensor with shape [batch_size] with the true label, 范围: [0, mnist.NUM_CLASSES). 注意 : tf.train.QueueRunner 被添加进 graph, 它必须用 tf.train.start_queue_runners() 来启动线程. """ if not num_epochs: num_epochs = None filename = os.path.join(FLAGS.train_dir, TRAIN_FILE if train else VALIDATION_FILE) with tf.name_scope('input'): # tf.train.string_input_producer 返回一个 QueueRunner,里面有一个 FIFQueue filename_queue = tf.train.string_input_producer( [filename], num_epochs=num_epochs) # 如果样本数据很大,可以分成若干文件,把文件名列表传入 # Even when reading in multiple threads, share the filename queue. image, label = read_and_decode(filename_queue) # Shuffle the examples and collect them into batch_size batches. # (Internally uses a RandomShuffleQueue.) # We run this in two threads to avoid being a bottleneck. images, sparse_labels = tf.train.shuffle_batch( [image, label], batch_size=batch_size, num_threads=2, capacity=1000 + 3 * batch_size, # Ensures a minimum amount of shuffling of examples. # 留下一部分队列,来保证每次有足够的数据做随机打乱 min_after_dequeue=1000) return images, sparse_labels def run_training(): """Train MNIST for a number of steps.""" # Tell TensorFlow that the model will be built into the default Graph. with tf.Graph().as_default(): # Input images and labels. images, labels = inputs(train=True, batch_size=FLAGS.batch_size, num_epochs=FLAGS.num_epochs) # 构建一个从推理模型来预测数据的图 logits = mnist.inference(images, FLAGS.hidden1, FLAGS.hidden2) # Add to the Graph the loss calculation. # 定义损失函数 loss = mnist.loss(logits, labels) # 将模型添加到图操作中 train_op = mnist.training(loss, FLAGS.learning_rate) # 初始化变量的操作 init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer()) # Create a session for running operations in the Graph. # 在图中创建一个用于运行操作的会话 sess = tf.Session() # 初始化变量,注意:string_input_product 内部创建了一个epoch计数器 sess.run(init_op) # Start input enqueue threads. coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) try: step = 0 while not coord.should_stop(): start_time = time.time() # Run one step of the model. The return values are # the activations from the `train_op` (which is # discarded) and the `loss` op. To inspect the values # of your ops or variables, you may include them in # the list passed to sess.run() and the value tensors # will be returned in the tuple from the call. _, loss_value = sess.run([train_op, loss]) duration = time.time() - start_time # Print an overview fairly often. if step % 100 == 0: print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value, duration)) step += 1 except tf.errors.OutOfRangeError: print('Done training for %d epochs, %d steps.' % (FLAGS.num_epochs, step)) finally: # 通知其他线程关闭 coord.request_stop() # Wait for threads to finish. coord.join(threads) sess.close() def main(_): run_training() if __name__ == '__main__': parser = argparse.ArgumentParser() parser.add_argument( '--learning_rate', type=float, default=0.01, help='Initial learning rate.' ) parser.add_argument( '--num_epochs', type=int, default=2, help='Number of epochs to run trainer.' ) parser.add_argument( '--hidden1', type=int, default=128, help='Number of units in hidden layer 1.' ) parser.add_argument( '--hidden2', type=int, default=32, help='Number of units in hidden layer 2.' ) parser.add_argument( '--batch_size', type=int, default=100, help='Batch size.' ) parser.add_argument( '--train_dir', type=str, default='/tmp/data', help='Directory with the training data.' ) FLAGS, unparsed = parser.parse_known_args() tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)