数据集高层操作

最新推荐文章于 2022-05-13 15:53:02 发布

zzb5233

最新推荐文章于 2022-05-13 15:53:02 发布

阅读量301

点赞数 1

分类专栏：机器学习&深度学习文章标签： tensorflow

本文链接：https://blog.csdn.net/zzb5233/article/details/82891413

版权

机器学习&深度学习专栏收录该内容

23 篇文章 0 订阅

订阅专栏

代码如下：

# -*- coding: utf-8 -*-
'''
Created on 2018年9月24日

@author: plus
'''


import tempfile
import tensorflow as tf

# 输入数据使用本章第一节（1. TFRecord样例程序.ipynb）生成的训练和测试数据。
train_files = tf.train.match_filenames_once("output.tfrecords")
test_files = tf.train.match_filenames_once("output_test.tfrecords")

# 解析一个TFRecord的方法。
def parser(record):
    features = tf.parse_single_example(
        record,
        features={
            'image_raw':tf.FixedLenFeature([],tf.string),
            'pixels':tf.FixedLenFeature([],tf.int64),
            'label':tf.FixedLenFeature([],tf.int64)
        })
    decoded_images = tf.decode_raw(features['image_raw'],tf.uint8)
    retyped_images = tf.cast(decoded_images, tf.float32)
    images = tf.reshape(retyped_images, [784])
    labels = tf.cast(features['label'],tf.int32)
    #pixels = tf.cast(features['pixels'],tf.int32)
    return images, labels


image_size = 299          # 定义神经网络输入层图片的大小。
batch_size = 100          # 定义组合数据batch的大小。
shuffle_buffer = 10000   # 定义随机打乱数据时buffer的大小。

# 定义读取训练数据的数据集。
dataset = tf.data.TFRecordDataset(train_files)
dataset = dataset.map(parser)

# 对数据进行shuffle和batching操作。这里省略了对图像做随机调整的预处理步骤。
dataset = dataset.shuffle(shuffle_buffer).batch(batch_size)

# 重复NUM_EPOCHS个epoch。
NUM_EPOCHS = 10
dataset = dataset.repeat(NUM_EPOCHS)

# 定义数据集迭代器。
iterator = dataset.make_initializable_iterator()
image_batch, label_batch = iterator.get_next()



# 定义神经网络的结构以及优化过程。这里与7.3.4小节相同。
def inference(input_tensor, weights1, biases1, weights2, biases2):
    layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
    return tf.matmul(layer1, weights2) + biases2

INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500
REGULARAZTION_RATE = 0.0001   
TRAINING_STEPS = 5000        

weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER1_NODE], stddev=0.1))
biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE]))

weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], stddev=0.1))
biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE]))

y = inference(image_batch, weights1, biases1, weights2, biases2)
    
# 计算交叉熵及其平均值
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=label_batch)
cross_entropy_mean = tf.reduce_mean(cross_entropy)
    
# 损失函数的计算
regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
regularaztion = regularizer(weights1) + regularizer(weights2)
loss = cross_entropy_mean + regularaztion

# 优化损失函数
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(loss)



# 定义测试用的Dataset。
test_dataset = tf.data.TFRecordDataset(test_files)
test_dataset = test_dataset.map(parser)
test_dataset = test_dataset.batch(batch_size)

# 定义测试数据上的迭代器。
test_iterator = test_dataset.make_initializable_iterator()
test_image_batch, test_label_batch = test_iterator.get_next()

# 定义测试数据上的预测结果。
test_logit = inference(test_image_batch, weights1, biases1, weights2, biases2)
predictions = tf.argmax(test_logit, axis=-1, output_type=tf.int32)
 
# 声明会话并运行神经网络的优化过程。
with tf.Session() as sess:  
    # 初始化变量。
    sess.run((tf.global_variables_initializer(),
              tf.local_variables_initializer()))
    
    # 初始化训练数据的迭代器。
    sess.run(iterator.initializer)
    
    # 循环进行训练，直到数据集完成输入、抛出OutOfRangeError错误。
    while True:
        try:
            sess.run(train_step)
        except tf.errors.OutOfRangeError:
            break

    test_results = []
    test_labels = []
    # 初始化测试数据的迭代器。
    sess.run(test_iterator.initializer)
    # 获取预测结果。
    while True:
        try:
            pred, label = sess.run([predictions, test_label_batch])
            test_results.extend(pred)
            test_labels.extend(label)
        except tf.errors.OutOfRangeError:
            break

# 计算准确率
correct = [float(y == y_) for (y, y_) in zip (test_results, test_labels)]
accuracy = sum(correct) / len(correct)
print("Test accuracy is:", accuracy)

tf.train.match_filenames_once:

tf.train.match_filenames_once(
pattern,
name=None
)

Args:

pattern: A file pattern (glob), or 1D tensor of file patterns.

name: A name for the operations (optional).

Returns:

A variable that is initialized to the list of files matching the pattern(s).

来获取文件列表。返回值为一个变量。<tf.Variable 'matching_filenames:0' shape=<unknown> dtype=string_ref>

tf.data.TFRecordDataset：

A Dataset comprising records from one or more TFRecord files.

Creates a TFRecordDataset to read for one or more TFRecord files.

NOTE: The num_parallel_reads argument can be used to improve performance when reading from a remote filesystem.

Args:

filenames: A tf.string tensor or tf.data.Dataset containing one or more filenames.

compression_type: (Optional.) A tf.string scalar evaluating to one of "" (no compression), "ZLIB", or "GZIP".

buffer_size: (Optional.) A tf.int64 scalar representing the number of bytes in the read buffer. 0 means no buffering.

num_parallel_reads: (Optional.) A tf.int64 scalar representing the number of files to read in parallel. Defaults to reading files sequentially.

从TFRecord 文件创边数据。TFRecord 文件格式是一种面向记录的简单二进制格式，很多 TensorFlow 应用采用此格式来训练数据。通过 tf.data.TFRecordDataset 类，您可以将一个或多个 TFRecord 文件的内容作为输入管道的一部分进行流式传输。

# Creates a dataset that reads all of the examples from two files.
filenames = ["/var/data/file1.tfrecord", "/var/data/file2.tfrecord"]
dataset = tf.data.TFRecordDataset(filenames)

TFRecordDataset 初始化程序的 filenames 参数可以是字符串、字符串列表，也可以是字符串 tf.Tensor。1中调用tf.train.match_filenames_once返回的即为一个tf.Tensor。