Tensorflow学习笔记十二——TensorFlow数据读取

数据读取方法总结有3种：
（1）预加载数据：预定义常量或变量来保存数据
（2）供给数据：在会话中运行run（）函数的时候通过复制给feed_dict参数的方式将数据注入placeholder中。
（3）从文件中读取数据：在TensorFlow图的起始，让一个输入管线从文件中读取数据。
12.1 TFRecord格式

message Example{
    Features features=1;
};
message Features{
  map<string,Feature> feature=1;  
};
message Feature{
    oneof kind{
        BytesList bytes_list=1;
        FloatList float_list=2;
        Int64List int64_list=3;
    }
};

下面通过一段代码将Fashion_MNIST数据集转化为TFRecord文件。大致过程就是：

• 将数据填入到Example协议内存块
• 将协议内存块序列化为一个字符串
• 通过io.TFRecordWriter类写入到TFRecord文件

 import tensorflow as tf
import numpy as np

(train_images,train_labels),(test_images,test_labels)=tf.keras.datasets.fashion_mnist.load_data()

def Int64_feature(value):
    return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
def Bytes_feature(value):
    return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

pixels=train_images.shape[1]
num_examples=train_images.shape[0]

filename="/home/xxy/TFRecord/fashion_MNIST.tfrecords"

writer=tf.io.TFRecordWriter(filename)

for i in range(num_examples):
    image_to_string=train_images[i].tostring()

    feature={
        "pixels":Int64_feature(pixels),
        "label":Int64_feature(train_labels[i]),
        "image_raw":Bytes_feature(image_to_string)
    }

    features=tf.train.Features(feature=feature)

    example=tf.train.Example(features=features)
    
    writer.write(example.SerializaToString())
print("writed ok")
writer.close()

使用data模块中的data.experimental模块中的TFRecordWriter类将Fashion_MNIIST数据集写入到一个TFRecord文件中：

import tensorflow as tf

(train_images,train_labels),(test_images,test_labels)=tf.keras.datasets.fashion_mnist.load_data()

def Int64_feature(value):
    return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
def Bytes_feature(value):
    return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

pixels=train_images.shape[1]
num_examples=train_images.shape[0]

filename="/home/xxy/TFRecord/fashion_MNIST2.tfrecords"

#writer=tf.io.TFRecordWriter(filename)
writer=tf.data.experimental.TFRecordWriter(filename)
def serialize_example(i):
    iamge_to_string=train_images[i].tostring()
    feature={
        "pixels":Int64_feature(pixels),
        "labels=":Int64_feature(train_labels[i]),
        "image_raw":Bytes_feature(image_to_string)
    }
    feature=tf.train.Feature(feature=feature)
    example_proto=tf.train.Example(features=features)
    return example_proto.SerializeToString()

def generator():
    for i in range(num_examples):
        yield serialize_example(i)

serialized_features_dataset=tf.data.Dataset.from_generator(generator,output_types=tf.string,outpt_shape=())

writer.write(serialized_features_dataset)

print("writed ok")
writer.close()

从TFRecord文件中解析数据：

import tensorflow as tf
filename="/home/xxy/TFRecord/fashion-MNIST.tfrecords"
tfrecord_dataset=tf.data.TFRecordDataset(filename)
''' test part
for sample in tfrecord_dataset.take(5):
    print(repr(sample)) 
'''

def parse_function(example_proto):
    feature=tf.io.parse_single_example(example_proto,
                                       features={
                                           "pixels":tf.io.FixedLenFeature([],tf.int64),
                                           "label":tf.io.FixedLenFeature([],tf.int64),
                                           "iamge_raw":tf.io.FixedLenFeature([],tf.string),
                                       })
    return feature

parsed_dataset=tfrecord_dataset.map(parse_function)

'''test code
print(parsed_dataset)
'''

for parsed_record in parsed_dataset.take(1):
    images=tf.io.decode_raw(parsed_record["image_raw"],tf.uint8)
    labels=tf.cast(parsed_record["label"],tf.int32)
    pixels=tf.cast(parsed_record["pixels"],tf.int32)
    print(images)
    print(labels)
    print(pixels)

12.2 CSV格式
csv-comma-Separated values,字符分隔值。以纯文本形式存储表格数据（数字和文本），这意味这该文件是一个字符序列，读取该文件不需要经过像二进制数据那样反序列化的过程。

    import tensorflow as tf
file_name="/home/xxy/CSV/data.csv"
CSV_CLOUMNS=['col1','col2','col3','col4']
csv_dataset=tf.data.experimental.make_csv_dataset(file_name,batch_size=10,shuffle=False,column_names=CSV_CLOUMNS,ignore_errors=True)
examples=next(iter(csv_dataset))
print(examples)
    

12.3 队列

import tensorflow as tf

Queue=tf.queue.FIFOQueue(2,"int32")

queue_init=Queue.enqueue_many(([10,100],))

for i in range(5):
    a=Queue.dequeue()
    b=a+10
    Queue_en=Queue.enqueue([b])
    print(a)

文件队列

import tensorflow as tf
import numpy as np

(train_images,train_labels),(test_images,test_labels)=tf.keras.datasets.fashion_mnist.load_data()

def _int64_feature(value):
    return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
def _bytes_feature(value):
    return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

pixels=test_images.shape[1]
num_examples=test_images.shape[0]
num_files=2

for i in range(num_files):
    filename=("/home/xxy/TFRecord/data_tfrecord-%.1d-of-%.1d"%(i,num_files))
    writer=tf.io.TFRecordWriter(filename)
    
    for index in range(num_examples):
        image_string=test_images[index].tostring()
        example=tf.train.Example(features=tf.train.Features(feature={
            "pixels":_int64_feature(pixels),
            "label":_int64_feature(np.argmax(test_labels[indes])),
            "image_raw":_bytes_feature(image_string)
        }))
        writer.write(example.SerializaToString())
print("writed ok")
writer.close()

import tensorflow as tf
files=tf.train.match_filenames_once("/home/xxy/TFRecord/data_tfrecords-*")
filename_queue=tf.train.string_input_producer(files,shuffle=False)
reader=tf.TFRecordReader()
_,Serialized_example=reader.read(filename_queue)

features=tf.parse_single_example(
    serialized_example,
    features={
        "image_raw":tf.FixedLenFeature([],tf.string),
        "pixels":tf.FixedLenFeature([],tf.int64),
        "label":tf.FixedLenFeature([],tf.int64)
    })
images=tf.decode_raw(features["image_raw"],tf.uint8)
lables=tf.cast(features["labels"],tf.int32)
pixels=tf.cast(features["pixels"],tf.int32)
with tf.Session() as sess:
    tf.global_variables_initializer().run()
    print(sess.run(files))
    
    coordinator=tf.train.Coordinator()
    threads=tf.train.start_queue_runners(sess=sess,coord=coordinator)
    
    for i in range(6):
        print(sess.run([images,labels]))
    
    coordinator.request_stop()
    coordinator.join(threads)

12.4 多线程处理输入的数据
1.使用coordinator类管理线程

• should_stop()：通过函数的返回值判断线程是否停止，如果线程停止了，则函数返回true
• request_stop()：请求该线程及其他线程停止
• join()：等待被指定的线程终止

 import tensorflow as tf
import nnumpy as np
import threading
import time

def Thread_op(coordinator,thread_id):
    while coordinator.should_stop() == False:
        if np.random.rand()<0.1:
            print("Stoping from thread_id : %d "% thread_id)
            coordinator.request_stop()
        else:
            print("Working on thread_id ； %d" % thread_id)
        time.sleep(10)
        
coordinator=tf.train.Coordinator()

threads=[threading.Thread(target=Thread_op,args=(coordinator,i)) for i in range(5)]

for j in threads:
    j.start()
    
coordinator.join(threads)

2.在Tensorflow1.x中使用QueueRunner创建线程

import tensorflow as tf
import nnumpy as np
import threading
import time
queue=tf.FIFOQueue(100,"float")
enqueue=queue.enqueue([tf.random_normal([10])])
qr=tf.train.QueueRunner(queue,[enqueue]*10)
tf.train.add_queue_runner(qr)
out_tensor=queue.dequeue()

with tf.Session() as sess:
    coordinator= tf.train.Coordinator()
    start_queue_runners(sess,coord,daemon,start,collection)
    threads=tf.train.start_queue_runners(sess=sess,coord=coordinator)
    
    for i in range(10):
        print(sess.run(out_tensor))
        
    coordinator.request_stop()
    coordinator.join(threads)

12.5 组织数据batch

import tensorflow as tf

file = tf.train.match_filename_once("/home/xxy/TFRecord/data_tfrecords-*")

filename_queue=tf.train.string_input_producer(files,shuffle=True)
reader=tf.TFRecordReader()

_,serialized_example=reader.read(filename_queue)

features=tf.parse_single_example(
    serialized_example,
    features={
        "image_raw":tf.FIxedLenFeature([],tf.string),
        "pixels":tf.FIxedLenFeature([],tf.int64),
        "label":tf.FIxedLenFeature([],tf.int64)
    })
images=tf.decode_raw(features["image_raw",tf.uint8])
labels=tf.cast(features["labels",tf.int32])
pixels=tf.cast(features["pixels",tf.int32])

batch_size=10

capacity=5000+3*batch_size
tf.train.batch([images,labels],batch_size=batch_size,capacity=capacity,)

with tf.Session() as sess:
    tf.global_variables_initializer().run()
    coord=tf.train.Coordinator()
    threads=tf.train.start_queue_runners(sess=sess,coord=coord)

    for i in range(3):
        xs,ys=sess.run([image_batch,label_batch])
        print(xs,ys)

    coord.request_stop()
    coord.join(threads)

import tensorflow as tf

(train_images,train_labels),(test_images,test_labels)=tf.keras.datasets.fashion_mnist.load_data()

train_images=train_images.reshape(60000,784).astype('float32')/255
test_images=train_images.reshape(1000,784).astype('float32')/255

train_datasets=tf.data.Dataset.from_tensor_slices((train_images,train_labels))
train_datasets=train_datasets.shuffle(buffer_size=1024).batch(100)

test_dataset=tf.data.Dataset.from_tensor_slices((test_images,test_labels))
test_dataset=test_dataset.batch(100)

for train_images,train_labels in train_datasets:
    print(train_images,train_labels)

import tensorflow as tf
import numpy as np

n_observations=int(1e4)
feature0=np.random.choice([False,True],n_observations)
feature1=np.random.randint(0,5,n_observations)
strings=np.array([b'cat',b'dog',b'chicken',b'horse',b'goat'])
feature2=strings[feature1]
feature3=np.random.randn(n_observations)
features_dataset=tf.data.Dataset.from_tensor_slices((feature0,feature1,feature2,feature3))

for fo,f1,f2,f3 in features_dataset.take(1):
    print(f0)
    print(f1)
    print(f2)
    print(f3)

import tensorflow as tf
import numpy as np

(train_images,train_labels),(test_images,test_labels)=tf.keras.datasets.fashion_mnist.load_data()

train_images=train_images.reshape(60000,784).astype('float32')/255
test_images=train_images.reshape(1000,784).astype('float32')/255

train_datasets=tf.data.Dataset.from_tensor_slices((train_images,train_labels))
train_datasets=train_datasets.shuffle(buffer_size=1024).batch(100)

for step,x_batch_train in enumerate(train_datasets):
    print(step,x_batch_train)