《面向机器智能的tensorflow实践》书中第5.5节的Stanford Dogs例程是入门TensorFlow的良好范例。但该书及其github中均没有提供完整代码，并且书中的部分代码因TensorFlow版本原因也存在无法运行的情况。作为TensorFlow小白，经过近2周的学习，终于实现了该节的完整代码，与大家分享。
本人运行的环境是：win7X64+Anaconda1.6.3+Spyder3.2.1+tensorflow1.1.0。将代码分为写tfrecord文件和训练测试模型两部分。大部分代码的解释在该书均可找到，我根据自己的理解又添加了部分注释。
1. 写tfrecord文件
代码如下：
# -*- coding: utf-8 -*-
"""
Created on Thu Nov 2 09:29:57 2017
@author: XM
读取Stanford Dog中的文件，并转换为tensorflow record格式，是进行训练的第1步
"""
import tensorflow as tf
import glob
from itertools import groupby
from collections import defaultdict
sess = tf.InteractiveSession()
#查找符合一定规则的所有文件，并将文件名以lis形式返回。
image_filenames_0 = glob.glob("./imagenet-dogs/n02*/*.jpg")
#这句是我添加的。因为读到的路径形式为：'./imagenet-dogs\\n02085620-Chihuahua\\n02085620_10074.jpg'，路径分隔符中除第1个之外，都是2个反斜杠，与例程不一致。这里将2个反斜杠替换为斜杠
image_filenames = list(
map(lambda image: image.replace('\\', '/'), image_filenames_0))
#用list类型初始化training和testing数据集，用defaultdict的好处是为字典中不存在的键提供默认值
training_dataset = defaultdict(list)
testing_dataset = defaultdict(list)
#将品种名从文件名中切分出，image_filename_with_breed是一个迭代器，用list(image_filename_with_breed)将其转换为list，其中的元素类似于：('n02085620-Chihuahua', './imagenet-dogs/n02085620-Chihuahua/n02085620_10131.jpg')。
image_filename_with_breed = map(
lambda filename: (filename.split("/")[2], filename), image_filenames)
## Group each image by the breed which is the 0th element in the tuple returned above
#groupby后得到的是一个迭代器，每个元素的形式为：('n02085620-Chihuahua', <itertools._grouper at 0xd5892e8>)，其中第1个元素为种类；第2个元素代表该类的文件，这两个元素也分别对应for循环里的dog_breed和breed_images。
for dog_breed, breed_images in groupby(image_filename_with_breed,
lambda x: x[0]):
#enumerate的作用是列举breed_images中的所有元素，可同时返回索引和元素，i和breed_image
#的最后一个值分别是：168、('n02116738-African_hunting_dog', './imagenet-dogs/
#n02116738-African_hunting_dog/n02116738_9924.jpg')
for i, breed_image in enumerate(breed_images):
#因为breed_images是按类分别存储的，所以下面是将大约20%的数据作为测试集，大约80%的
#数据作为训练集。
#testing_dataset和training_dataset是两个字典，testing_dataset中
#的第一个元素是 'n02085620-Chihuahua': ['./imagenet-dogs/n02085620-Chihuahua/
#n02085620_10074.jpg', './imagenet-dogs/n02085620-Chihuahua/
#n02085620_11140.jpg',.....]
if i % 5 == 0:
testing_dataset[dog_breed].append(breed_image[1])
else:
training_dataset[dog_breed].append(breed_image[1])
# 测试每种类型下的测试集是否至少包含了18%的数据
breed_training_count = len(training_dataset[dog_breed])
breed_testing_count = len(testing_dataset[dog_breed])
assert round(breed_testing_count /
(breed_training_count + breed_testing_count),
2) > 0.18, "Not enough testing images."
def write_records_file(dataset, record_location):
"""
Fill a TFRecords file with the images found in `dataset` and include their category.
Parameters
----------
dataset : dict(list)
Dictionary with each key being a label for the list of image filenames of its value.
record_location : str
Location to store the TFRecord output.
"""
writer = None
# Enumerating the dataset because the current index is used to breakup the files if they get over 100
# images to avoid a slowdown in writing.
current_index = 0
#遍历每一种类型的所有文件
for breed, images_filenames in dataset.items():
#遍历每一个文件
for image_filename in images_filenames:
if current_index % 100 == 0:
if writer:
writer.close()
#创建tensorflow record的文件名
record_filename = "{record_location}-{current_index}.tfrecords".format(
record_location=record_location,
current_index=current_index)
writer = tf.python_io.TFRecordWriter(record_filename)
current_index += 1
image_file = tf.read_file(image_filename)
#将图片按照jpeg格式解析，ImageNet dogs中有些图片按照JPEG解析时会出错，用try
#语句忽视解析错误的图片。
try:
image = tf.image.decode_jpeg(image_file)
except:
print(image_filename)
continue
# 转换为灰度图像.
grayscale_image = tf.image.rgb_to_grayscale(image)
#此处做了修改，resize_images的第二个参数要求是tensor，原代码有误。
#resized_image = tf.image.resize_images(grayscale_image, 250, 151)
resized_image = tf.image.resize_images(grayscale_image, [250, 151])
# tf.cast is used here because the resized images are floats but haven't been converted into
# image floats where an RGB value is between [0,1).
image_bytes = sess.run(tf.cast(resized_image, tf.uint8)).tobytes()
# Instead of using the label as a string, it'd be more efficient to turn it into either an
# integer index or a one-hot encoded rank one tensor.
# https://en.wikipedia.org/wiki/One-hot
#将表示种类的字符串转换为python默认的utf-8格式，防止有问题
image_label = breed.encode("utf-8")
## 创建一个 example protocol buffer 。
# 其中，feature={
# 'label':
# tf.train.Feature(bytes_list=tf.train.BytesList(value=[image_label])),
# 'image':
# tf.train.Feature(bytes_list=tf.train.BytesList(value=[image_bytes]))
# })是创建1个属性
example = tf.train.Example(
features=tf.train.Features(feature={
'label':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[image_label])),
'image':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[image_bytes]))
}))
#SerializeToString()将文件序列化为二进制字符串
writer.write(example.SerializeToString())
writer.close()
#分别将测试数据和训练数据写入tensorflow record，分别保存在文件夹./output/testing-images/和./output/
#training-images/下面。
write_records_file(testing_dataset, "./output/testing-images/testing-image")
write_records_file(training_dataset, "./output/training-images/training-image")
几个注意事项：
（1） 在保存成tfrecord文件之前，要先在代码的路径下新建./output/testing-images/和./output/training-images/这两个目录，不然会报错。
（2）在cpu上程序完全执行下来耗时较长，我的DELL xps执行了将近18个小时。执行时有报错，报错信息为：
InvalidArgumentError: Invalid JPEG data, size 107746
[[Node: DecodeJpeg_15166 = DecodeJpeg[acceptable_fraction=1, channels=0, dct_method="", fancy_upscaling=true, ratio=1, try_recover_truncated=false, _device="/job:localhost/replica:0/task:0/cpu:0"](ReadFile_15166)]]stackflow上有人问到这个问题，说原因是执行时在pc上拔插了U盘，我也确实拔插了U盘，当时没注意执行情况，然后去吃饭了，吃饭回来发现报错停止了。这时，可以重新开始保存，也可以先查看保存到多少个文件了，将代码中的write_records_file函数简单修改后，继续保存。我修改的代码如下：
def write_records_file(dataset, record_location):
"""
Fill a TFRecords file with the images found in `dataset` and include their category.
Parameters
----------
dataset : dict(list)
Dictionary with each key being a label for the list of image filenames of its value.
record_location : str
Location to store the TFRecord output.
"""
writer = None
# Enumerating the dataset because the current index is used to breakup the files if they get over 100
# images to avoid a slowdown in writing.
current_index = 0
for breed, images_filenames in dataset.items():
for image_filename in images_filenames:
# current_index += 1
# cc = current_index-1
#我的执行结果中，tfrecord文件的序号到了11000，前面的就不管了，后面的继续执行保存文件操作。
if current_index >= 11000:
if current_index % 100 == 0:
if writer:
writer.close()
record_filename = "{record_location}-{current_index}.tfrecords".format(
record_location=record_location,
current_index=current_index)
# print(record_filename)
writer = tf.python_io.TFRecordWriter(record_filename)
# current_index += 1
image_file = tf.read_file(image_filename)
# In ImageNet dogs, there are a few images which TensorFlow doesn't recognize as JPEGs. This
# try/catch will ignore those images.
try:
image = tf.image.decode_jpeg(image_file)
except:
print(image_filename)
continue
# Converting to grayscale saves processing and memory but isn't required.
grayscale_image = tf.image.rgb_to_grayscale(image)
# resized_image = tf.image.resize_images(grayscale_image, 250, 151)
resized_image = tf.image.resize_images(grayscale_image,
[250, 151])
# tf.cast is used here because the resized images are floats but haven't been converted into
# image floats where an RGB value is between [0,1).
image_bytes = sess.run(tf.cast(resized_image,
tf.uint8)).tobytes()
# Instead of using the label as a string, it'd be more efficient to turn it into either an
# integer index or a one-hot encoded rank one tensor.
# https://en.wikipedia.org/wiki/One-hot
image_label = breed.encode(
"utf-8") #这个是担心有中文字符吗？——肖蒙2017年11月1日16:24:17
example = tf.train.Example(
features=tf.train.Features(feature={
'label':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[image_label])),
'image':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[image_bytes]))
}))
writer.write(example.SerializeToString())
current_index += 1
writer.close()
2.训练与测试
代码如下：
# -*- coding: utf-8 -*-
"""
Created on Thu Nov 2 09:29:57 2017
@author: XM
读取第1步保存的tensorflow record文件，并进行训练
程序中提到的书本均指《面向机器智能的tensorflow实践》
"""
import tensorflow as tf
from tensorflow.python.ops import random_ops
import glob
BATCH_SIZE = 10
IMAGE_WIDTH = 250
IMAGE_HEIGHT = 151
#———————————————————————————————————————图像预处理————————————————————————————————————————————
#从文件队列中读取batch_size个文件，用于训练或测试
def read_tfrecord(serialized, batch_size):
#parse_single_example解析器将中的example协议内存块解析为张量，
#每个tfrecord中有多幅图片，但parse_single_example只提取单个样本，
#parse_single_example只是解析tfrecord，并不对图像进行解码
features = tf.parse_single_example(
serialized,
features={
'label': tf.FixedLenFeature([], tf.string),
'image': tf.FixedLenFeature([], tf.string),
})
#将图像文件解码为uint8，因为所有通道的信息都处于0~255，然后reshape
record_image = tf.decode_raw(features['image'], tf.uint8)
image = tf.reshape(record_image, [IMAGE_WIDTH, IMAGE_HEIGHT, 1])
#将label平化为字符串
label = tf.cast(features['label'], tf.string)
#用于生成batch的缓冲队列的大小，下面采用的是经验公式
min_after_dequeue = 1000
capacity = min_after_dequeue + 3 * batch_size
#生成image_batch和label_batch
image_batch, label_batch = tf.train.shuffle_batch(
[image, label],
batch_size=batch_size,
capacity=capacity,
min_after_dequeue=min_after_dequeue)
return image_batch, label_batch
# Converting the images to a float of [0,1) to match the expected input to convolution2d
def convert_image(image_batch):
return (tf.image.convert_image_dtype(image_batch, tf.float32))
# Match every label from label_batch and return the index where they exist in the list of classes
def find_index_label(label_batch):
return (tf.map_fn(
lambda l: tf.where(tf.equal(labels_all, l))[0, 0:1][0],
label_batch,
dtype=tf.int64))
#————————————————————————————————————————创建CNN————————————————————————————————————————————————
#占位符，None代表输入的数据个数不确定
image_holder = tf.placeholder(tf.float32,
[BATCH_SIZE, IMAGE_WIDTH, IMAGE_HEIGHT, 1])
label_holder = tf.placeholder(tf.int64, [BATCH_SIZE])
keep_prob_holder = tf.placeholder(tf.float32) #dropout保留的比例
#此部分代码是创建卷积层时weights_initializer用到的初始化函数，
#书中代码没有此部分，是新添加的
def weights_initializer_random_normal(shape,
dtype=tf.float32,
partition_info=None):
return random_ops.random_normal(shape)
#h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#第1层卷积————————————————————————
with tf.name_scope("conv1") as scope:
#这里用的是高级层，而不是标准层tf.nn.conv2d，二者的区别见书本第5.3.5节
conv2d_layer_one = tf.contrib.layers.convolution2d(
image_holder,
#产生滤波器的数量，书中代码有误
num_outputs=32,
#num_output_channels=32,
#核尺寸
kernel_size=(5, 5),
#激活函数
activation_fn=tf.nn.relu,
#权值初始化，书中代码有误：
#1、weight_init应该是weights_initializer；
#2、写成tf.random_normal会报错：random_normal() got an unexpected keyword argument 'partition_info'，
weights_initializer=weights_initializer_random_normal,
# weight_init=tf.random_normal,
stride=(2, 2),
trainable=True)
#第1层池化————————————————————————————————
with tf.name_scope("pool1") as scope:
pool_layer_one = tf.nn.max_pool(
conv2d_layer_one,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
#第2层卷积————————————————————————————————
with tf.name_scope("conv2") as scope:
conv2d_layer_two = tf.contrib.layers.convolution2d(
pool_layer_one,
#修改，原因同第1层
num_outputs=64,
#num_output_channels=64,
kernel_size=(5, 5),
activation_fn=tf.nn.relu,
#修改，原因同第1层
weights_initializer=weights_initializer_random_normal,
#weight_init=tf.random_normal,
stride=(1, 1),
trainable=True)
#第2层池化————————————————————————————————
with tf.name_scope("pool2") as scope:
pool_layer_two = tf.nn.max_pool(
conv2d_layer_two,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
#展开层，展开为秩1张量——————————————————————
with tf.name_scope("flat") as scope:
flattened_layer_two = tf.reshape(pool_layer_two, [BATCH_SIZE, -1])
#全连接层1—————————————————————————————————
with tf.name_scope("full_connect1") as scope:
hidden_layer_three = tf.contrib.layers.fully_connected(
flattened_layer_two,
512,
#修改，原因同第1层
weights_initializer=lambda i, dtype, partition_info=None: tf.truncated_normal([38912, 512], stddev=0.1),
#weight_init=lambda i, dtype: tf.truncated_normal([38912, 512], stddev=0.1),
activation_fn=tf.nn.relu)
#小trick：dropout
hidden_layer_three = tf.nn.dropout(hidden_layer_three, keep_prob_holder)
#全连接层2—————————————————————————————————
with tf.name_scope("full_connect2") as scope:
final_fully_connected = tf.contrib.layers.fully_connected(
hidden_layer_three,
120,
#修改，原因同第1层
weights_initializer=lambda i, dtype, partition_info=None: tf.truncated_normal([512, 120], stddev=0.1)
#weight_init=lambda i, dtype: tf.truncated_normal([512, 120], stddev=0.1)
)
#输出———————————————————————
with tf.name_scope("output") as scope:
logits = final_fully_connected
#查找排名第1的分类结果是否是实际的种类
top_k_op = tf.nn.in_top_k(logits, label_holder, 1)
#————————————————————————————————————————loss————————————————————————————————————————————————
#计算交叉熵
def loss(logits, labels):
#按照tensorflow1.0以上版本修改
#logits是全连接层的输出，不需softmax归一化，因为sparse_softmax_cross_entropy_with_logits函数会先将logits进行softmax归一化，然后与label表示的onehot向量比较，计算交叉熵。
return tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(
logits=logits, labels=labels))
#————————————————————————————————————————training———————————————————————————————————————————————
#模型训练
def training(loss_value, learning_rate, batch):
return tf.train.AdamOptimizer(learning_rate, 0.9).minimize(
loss_value, global_step=batch)
#————————————————————————————————————————主函数——————————————————————————————————————————————————
if __name__ == '__main__':
#下面的几句是我添加的，因为我这里读到的路径形式为：'./imagenet-dogs\\n02085620-Chihuahua\\'，路径分隔符中除第1个之外，都是2个反斜杠，与例程不一致。这里将2个反斜杠替换为斜杠。
#glob.glob 用于获取所有匹配的路径
glob_path = glob.glob("./imagenet-dogs/*")
glob_path2 = list(map(lambda image: image.replace('\\', '/'), glob_path))
#读取所有的label，形式为n02085620-Chihuahua....
labels_all = list(map(lambda c: c.split("/")[-1], glob_path2))
#将所有的文件名列表（由函数tf.train.match_filenames_once匹配产生）
#生成一个队列，供后面的文件阅读器reader读取
#训练数据队列
filename_queue_train = tf.train.string_input_producer(
tf.train.match_filenames_once("./output/training-images/*.tfrecords"))
#测试数据队列
filename_queue_test = tf.train.string_input_producer(
tf.train.match_filenames_once("./output/testing-images/*.tfrecords"))
#创建tfrecord阅读器，并读取数据。
#默认shuffle=True，将文件打乱
reader = tf.TFRecordReader()
_, serialized_train = reader.read(filename_queue_train)
_, serialized_test = reader.read(filename_queue_test)
#读取训练数据——————————————————————————————————
train_image_batch, train_label_batch = read_tfrecord(
serialized_train, BATCH_SIZE)
# Converting the images to a float of [0,1) to match the expected input to convolution2d
train_images_op = convert_image(train_image_batch)
# Match every label from label_batch and return the index where they exist in the list of classes
train_labels_op = find_index_label(train_label_batch)
#读取测试数据——————————————————————————————————
test_image_batch, test_label_batch = read_tfrecord(serialized_test,
BATCH_SIZE)
# Converting the images to a float of [0,1) to match the expected input to convolution2d
test_images_op = convert_image(test_image_batch)
# Match every label from label_batch and return the index where they exist in the list of classes
test_labels_op = find_index_label(test_label_batch)
#————————————————————————————————————————————
batch = tf.Variable(0)
learning_rate = tf.train.exponential_decay(
0.01, batch * 3, 120, 0.95, staircase=True)
loss_op = loss(logits, train_labels_op)
train_op = training(loss_op, learning_rate, batch)
sess = tf.InteractiveSession()
#必须同时有全局变量和局部变量的初始化，不然会报错：
#OutOfRangeError (see above for traceback): RandomShuffleQueue '_134_shuffle_batch_8/random_shuffle_queue' is closed and has insufficient elements (requested 3, current size 0)
sess.run(tf.local_variables_initializer())
sess.run(tf.global_variables_initializer())
#声明一个Coordinator类来协同多个线程
coord = tf.train.Coordinator()
# 开始 Queue Runners (队列运行器)
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
#执行训练————————————————————————————————————————————
for j in range(1000):
train_images = sess.run(train_images_op)
train_labels = sess.run(train_labels_op)
train_logits, train_result, _ = sess.run(
[logits, top_k_op, train_op],
feed_dict={
image_holder: train_images,
label_holder: train_labels,
keep_prob_holder: 0.1
})
if j % 10 == 0:
# print(train_labels)
# print(train_result)
print("loss = ",
sess.run(
loss_op,
feed_dict={
image_holder: train_images,
label_holder: train_labels,
keep_prob_holder: 0.1
}), 't=', j)
#测试————————————————————————————————————————————
#每次的准确率
accurary_once_op = tf.reduce_mean(tf.cast(top_k_op, tf.float32))
#测试轮数
test_num = 0
#测试总准确度
accuracy_total = 0
for i in range(100):
test_images = sess.run(test_images_op)
test_labels = sess.run(test_labels_op)
accuracy_once = sess.run(
accurary_once_op,
feed_dict={
image_holder: test_images,
label_holder: test_labels,
keep_prob_holder: 1.0
})
accuracy_total = accuracy_total + accuracy_once
test_num = test_num + 1
if i % 10 == 0:
print("第", i, "轮测试，准确率为：", accuracy_total / test_num)
print("总准确率为：", accuracy_total / test_num)
# if i%10 == 0:
# print("次数：",i,"————————————————————————————————")
# print(test_labels)
# print(test_result)
#结束————————————————————————————————————————————
#通知其他线程退出
coord.request_stop()
#等待所有线程退出
coord.join(threads)
sess.close()其中的训练轮数和测试次数均可以修改。
扫一扫
3378
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
