标签:回话 type instance ssi 节点 city 其他 多个 lob
import tensorflow as tf
def _int64_feature(value):
# value必须是可迭代对象
# 非int的数据使用bytes取代int64即可
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
num_shards = 2
instance_perPshard = 2
for i in range(num_shards):
filename = (‘FTR/data.tfrecords-%.5d-of-%.5d‘ % (i, num_shards))
writer = tf.python_io.TFRecordWriter(filename) #<---------书写器打开
for j in range(instance_perPshard):
example = tf.train.Example(features=tf.train.Features(feature={ #<---------书写入缓冲区
‘i‘:_int64_feature(i),
‘j‘:_int64_feature(j)
}))
writer.write(example.SerializeToString()) #<---------书写入实际文件
writer.close() #<---------书写器关闭
默认多线程,这个默认的多线程过程用于维护文件名队列
‘‘‘读取TFR‘‘‘
files = ["FTR/data.tfrecords-00000-of-00002","FTR/data.tfrecords-00001-of-00002"]
# files = tf.train.match_filenames_once("FTR/data.tfrecords-*")
# 输入文件名列表
# 返回QueueRunner & FIFOQueue
# 打乱顺序&加入队列 和 输出队列获取文件 属于单独的线程
filename_queue = tf.train.string_input_producer(files, shuffle=False) #<---------输入文件队列
reader = tf.TFRecordReader() #<---------读取器打开
_,serialized_example = reader.read(filename_queue) #<---------读取原始文件
features = tf.parse_single_example( #<---------读取解析后文件
serialized_example,
features={
‘i‘:tf.FixedLenFeature([],tf.int64),
‘j‘:tf.FixedLenFeature([],tf.int64)
})
with tf.Session() as sess:
tf.global_variables_initializer().run()
coord = tf.train.Coordinator() #<---------多线程
threads = tf.train.start_queue_runners(sess=sess,coord=coord) #<---------文件名队列填充线程启动
for i in range(6):
print(sess.run([features[‘i‘],features[‘j‘]])) #<---------实际会话中启动读取过程
coord.request_stop() #<---------多线程
coord.join(threads) #<---------多线程
打包机制:
——————多线程调用前面的节点计算入队
——————批量出队并打包
所以不需要修改解析读取数据过程为循环之类的,可以说很是方便
example_batch, label_batch = tf.train.batch([example, label], #<---------多线程batch生成
batch_size=batch_size,
num_threads=3,
capacity=capacity)
example_batch, label_batch = tf.train.shuffle_batch([example, label], #<---------多线程随机batch生成
batch_size=batch_size,
num_threads=3,
capacity=capacity,
min_after_dequeue=30) 由于元素太少随机意义就不大了,所以多了个参数
files = ["FTR/data.tfrecords-00000-of-00002","FTR/data.tfrecords-00001-of-00002"]
# files = tf.train.match_filenames_once("FTR/data.tfrecords-*")
# 输入文件名列表
# 返回QueueRunner & FIFOQueue
# 打乱顺序&加入队列 和 输出队列获取文件 属于单独的线程
filename_queue = tf.train.string_input_producer(files, shuffle=False) #<---------输入文件队列
reader = tf.TFRecordReader() #<---------读取
_,serialized_example = reader.read(filename_queue) #<---------读取
features = tf.parse_single_example( #<---------读取
serialized_example,
features={
‘i‘:tf.FixedLenFeature([],tf.int64),
‘j‘:tf.FixedLenFeature([],tf.int64)
})
example, label = features[‘i‘], features[‘j‘]
batch_size = 2
capacity = 1000 + 3 * batch_size
# 入队单个样例,出队batch
# 可以指定多个线程同时执行入队操作
example_batch, label_batch = tf.train.batch([example, label], #<---------多线程batch生成
batch_size=batch_size,
num_threads=3,
capacity=capacity)
with tf.Session() as sess:
tf.global_variables_initializer().run()
coord = tf.train.Coordinator() #<---------多线程管理器
threads = tf.train.start_queue_runners(sess=sess,coord=coord) #<---------文件名队列填充线程启动
for i in range(3):
cur_example_batch, cur_label_batch = sess.run([example_batch, label_batch])
print(cur_example_batch, cur_label_batch)
coord.request_stop() #<---------多线程关闭
coord.join(threads)
这个输出每一行前为image(代指),后为label,第一行的数据对实际为0-0,0-1:
[0 0] [0 1] [1 1] [0 1] [0 0] [0 1]
read的二进制数据直接进行_bytes_feature化就可以写入文件,使用tf.string类型读出图片数据后可以直接decode解码之(推测tf中string对应二进制数据类型)。
把一张图片写入TFR中:
import tensorflow as tf
import matplotlib.pyplot as plt
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
img_raw = tf.gfile.FastGFile(‘123123.jpeg‘,‘rb‘).read()
filename = (‘FTR/image.tfrecords‘)
writer = tf.python_io.TFRecordWriter(filename) #<---------书写
example = tf.train.Example(features=tf.train.Features(feature={ #<---------书写
‘image‘:_bytes_feature(img_raw),
‘label‘:_int64_feature(1)
}))
writer.write(example.SerializeToString()) #<---------书写
writer.close()
从TFR中读取图片数据并解码绘制出来:
filename_queue = tf.train.string_input_producer([‘FTR/image.tfrecords‘], shuffle=False) #<---------输入文件队列
reader = tf.TFRecordReader() #<---------读取
_,serialized_example = reader.read(filename_queue) #<---------读取
features = tf.parse_single_example( #<---------读取
serialized_example,
features={
‘image‘:tf.FixedLenFeature([],tf.string),
‘label‘:tf.FixedLenFeature([],tf.int64)
})
img = tf.image.decode_jpeg(features[‘image‘])
with tf.Session() as sess:
tf.global_variables_initializer().run()
coord = tf.train.Coordinator() # <---------多线程
threads = tf.train.start_queue_runners(sess=sess, coord=coord) # <---------文件名队列填充线程启动
# img_raw, label = sess.run([features[‘image‘], features[‘label‘]])
image = sess.run(img)
plt.imshow(image)
plt.show()
coord.request_stop() # <---------多线程
coord.join(threads) # <---------多线程
仅仅示范了维护图片文件名队列的读写,没有过多的其他操作
reader = tf.WholeFileReader():新的读取器,应该是范用性二进制文件读取器
# 导入tensorflow
import tensorflow as tf
# 新建一个Session
with tf.Session() as sess:
# 我们要读三幅图片A.jpg, B.jpg, C.jpg
filename = [‘123.png‘, ‘123123.jpeg‘]
# string_input_producer会产生一个文件名队列
filename_queue = tf.train.string_input_producer(filename, shuffle=False, num_epochs=5)
# reader从文件名队列中读数据。对应的方法是reader.read
reader = tf.WholeFileReader() #<---------注意读取器不一样了
key, value = reader.read(filename_queue)
# tf.train.string_input_producer定义了一个epoch变量,要对它进行初始化
tf.local_variables_initializer().run()
# 使用start_queue_runners之后,才会开始填充队列
threads = tf.train.start_queue_runners(sess=sess)
i = 0
while True:
i += 1
# 获取图片数据并保存
image_data = sess.run(value)
with open(‘test_%d.jpg‘ % i, ‘wb‘) as f:
f.write(image_data)
文件名队列创建->读取解析文件->打包解析好的文件->多线程启动图训练(多线程指被使用的部分其实还是文件读取)
import tensorflow as tf
‘‘‘创建文件列表‘‘‘
files = tf.train.match_filenames_once("Records/output.tfrecords")
filename_queue = tf.train.string_input_producer(files, shuffle=False)
‘‘‘解析TFRecord文件里的数据‘‘‘
# 读取文件。
reader = tf.TFRecordReader()
_,serialized_example = reader.read(filename_queue)
# 解析读取的样例。
features = tf.parse_single_example(
serialized_example,
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)
labels = tf.cast(features[‘label‘],tf.int32)
#pixels = tf.cast(features[‘pixels‘],tf.int32)
images = tf.reshape(retyped_images, [784])
‘‘‘将文件以100个为一组打包‘‘‘
min_after_dequeue = 10000
batch_size = 100
capacity = min_after_dequeue + 3 * batch_size
image_batch, label_batch = tf.train.shuffle_batch([images, labels],
batch_size=batch_size,
capacity=capacity,
min_after_dequeue=min_after_dequeue)
‘‘‘训练模型‘‘‘
def inference(input_tensor, weights1, biases1, weights2, biases2):
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
return tf.matmul(layer1, weights2) + biases2
# 模型相关的参数
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)
# 初始化回话并开始训练过程。
with tf.Session() as sess:
tf.global_variables_initializer().run()
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# 循环的训练神经网络。
for i in range(TRAINING_STEPS):
if i % 1000 == 0:
print("After %d training step(s), loss is %g " % (i, sess.run(loss)))
sess.run(train_step)
coord.request_stop()
coord.join(threads)
『TensorFlow』队列&多线程&TFRecod文件_我辈当高歌
标签:回话 type instance ssi 节点 city 其他 多个 lob
原文地址:http://www.cnblogs.com/hellcat/p/6941446.html