Tensorflow化骨绵掌第2式-CIFAR-10与ImageNet图像识别
1、下载CIFAR-10数据集
CIFAR-10数据集包含10个类别的RGB彩色图片,图片尺寸为32×32,这十个类别包括:飞机、汽车、鸟、猫、鹿、狗、蛙、马、船、卡车。一共有50000张训练图片和10000张测试图片。
CIFAR-10数据集的特点:
(1)CIFAR-10是RGB的图片
(2)CIFAR-10的图片的大小是32*32
(3)CIFAR-10的图片来源大自然的真是物体,噪声大,图像比例、特征不是完全相同的,对识别带来一定的难度。
CIFAR-10官方文档有: https://github.com/tensorflow/models.git
文件 | 作用 |
---|---|
cifar10_input.py | 读取本地CIFAR-10的二进制文件格式的内容。 |
cifar10.py | 建立CIFAR-10的模型。 |
cifar10_train.py | 在CPU或GPU上训练CIFAR-10的模型。 |
cifar10_multi_gpu_train.py | 在多GPU上训练CIFAR-10的模型。 |
cifar10_eval.py | 评估CIFAR-10模型的预测性能。 |
下载数据集代码:
# coding:utf-8
# 引入当前目录中的已经编写好的cifar10模块
import cifar10
# 引入tensorflow
import tensorflow as tf
# tf.app.flags.FLAGS是TensorFlow内部的一个全局变量存储器,同时可以用于命令行参数的处理
FLAGS = tf.app.flags.FLAGS
# 在cifar10模块中预先定义了f.app.flags.FLAGS.data_dir为CIFAR-10的数据路径
# 我们把这个路径改为cifar10_data
FLAGS.data_dir = 'cifar10_data/'
# 如果不存在数据文件,就会执行下载
cifar10.maybe_download_and_extract()
下载完数据后提示:
》》Downloading cifar-10-binary.tar.gz 100.0%
Successfully downloaded cifar-10-binary.tar.gz 170052171 bytes
当然如果下载失败的话,可以去tensorflow官方进行下载数据集:
http://www.cs.toronto.edu/~kriz/cifar.html
2、介绍读取机制
①介绍原始读取机制
事实上,我们的程序必须将数据读入才能进行计算,假设读入时间是0.1s,计算时间是0.9s,那么意味着每运行1s时间,GPU有0.1并没有进行运行,这就浪费了时间、降低了运行效率。
在操作中,训练数据只使用了一个进程。
(1)先将数据从硬盘加载到内存中
(2)将数据交给CPU或者GPU进行运算。
②tensorflow读取机制
为了解决传统读取的问题,tensorflow中可以采用“文件队列名+内存队列”双队列的形式进行读取文件,可以很好的管理epoch文件,将整个读取训练过程分成两个线程。
下面以数据集A.jpg、B.jpg、C.jpg为例,假设读取一个epoch,那么就在文件队列名中A、B、C分别放入一次,并在后面的标注队列结束。
程序运行后,首先A文件写入内存队列,此时从文件名队列出队。
再一次读入B、C文件。
此时,在读入图片,系统会进行报错,检测到“结束”,自动跑出一个异常,外部捕捉到这个异常后结束程序。
假设在当前文件已有A.jpg、B.jpg、C.jpg三张图片,希望读取这三张图片的5个epoch并且把读取的结果重新保存到read文件夹中。
读取代码如下:
# coding:utf-8
import os
if not os.path.exists('read'):
os.makedirs('read/')
# 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 = ['A.jpg', 'B.jpg', 'C.jpg']
# 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()
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('read/test_%d.jpg' % i, 'wb') as f:
f.write(image_data)
# 程序最后会抛出一个OutOfRangeError,这是epoch跑完,队列关闭的标志
这里使用 filename_queue = tf.train.string_input_producer(filename, shuffle=False, num_epochs=5)建立一个可以运行5个epoch的文件名队列。并且使用reader读取,reader每次读取一张图片并保存。
如果设置filename_queue = tf.train.string_input_producer(filename, shuffle=Ture, num_epochs=5)时,那么每个epoch内的图像都可以被打乱。
3、实验:将CIFAR-10数据集保存为图片形式
在CIFAR-10数据集中,文件data_batch_1.bin、data_batch_2.bin、…、data_batch_5.bin和test_batch.bin中各有10000个样本。一个样本由3073个字节构成,第一个字节为标签(label),剩下3072个字节为图像数据。
如何读取CIFAR-10数据集,具体如下所示:
(1)用tf.train.string_input_producer建立队列
(2)通过reader.read读数据。一个文件就是一张图像,因此用的reader是tf.WholeFileReader()。CIFAR-10数据集是以固定字节存在文件中的,一个文件中包含有多个样本,因此不能使用tf.WholeFileReader(),而用的是tf.FixedLengthRecordReader()。
(3)调用tf.train.start_queue_runners。
(4)通过sess.run()取出图片结果.
代码解析:
(1)下载cifar-10数据集
# 查看CIFAR-10数据是否存在,如果不存在则下载并解压
def download():
# tf.app.flags.FLAGS是tensorflow的一个内部全局变量存储器
FLAGS = tf.app.flags.FLAGS
# 为了方便,我们将这个路径改为当前位置
FLAGS.data_dir = './cifar10_data'
# 如果不存在数据文件则下载,并且解压
cifar10.maybe_download_and_extract()
(2)设置图片保存路径
#将获取的图片保存到这里
image_save_path = './cifar10_image/'
if os.path.exists(image_save_path) == False:
os.mkdir(image_save_path)
(3)根据tensorflow读取机制,设置文件名队列
#检测CIFAR-10数据是否存在,如果不存在则返回False
def check_cifar10_data_files(filenames):
for file in filenames:
if os.path.exists(file) == False:
print('Not found cifar10 data.')
return False
return True
#获取图片前的预处理,检测CIFAR10数据是否存在,如果不存在直接退出
#如果存在,用string_input_producer函数创建文件名队列,
# 并且通过get_record函数获取图片标签和图片数据,并返回
def get_image(data_path):
filenames = [os.path.join(data_path, "data_batch_%d.bin" % i) for i in range(1, 6)]
print(filenames)
if check_cifar10_data_files(filenames) == False:
exit()
queue = tf.train.string_input_producer(filenames)
return get_record(queue)
(4)读取并解析图片
#获取每个样本数据,样本由一个标签+一张图片数据组成
def get_record(queue):
print('get_record')
#定义label大小,图片宽度、高度、深度,图片大小、样本大小
label_bytes = 1
image_width = 32
image_height = 32
image_depth = 3
image_bytes = image_width * image_height * image_depth
record_bytes = label_bytes + image_bytes
#根据样本大小读取数据
reader = tf.FixedLengthRecordReader(record_bytes)
key, value = reader.read(queue)
#将获取的数据转变成一维数组
#例如
# source = 'abcde'
# record_bytes = tf.decode_raw(source, tf.uint8)
#运行结果为[ 97 98 99 100 101]
record_bytes = tf.decode_raw(value, tf.uint8)
#获取label,label数据在每个样本的第一个字节
label_data = tf.cast(tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
#获取图片数据,label后到样本末尾的数据即图片数据,
# 再用tf.reshape函数将图片数据变成一个三维数组
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],[label_bytes + image_bytes]),
[3, 32, 32])
#矩阵转置,上面得到的矩阵形式是[depth, height, width],即红、绿、蓝分别属于一个维度的,
#假设只有3个像素,上面的格式就是RRRGGGBBB
#但是我们图片数据一般是RGBRGBRGB,所以这里要进行一下转置
#注:上面注释都是我个人的理解,不知道对不对
image_data = tf.transpose(depth_major, [1, 2, 0])
#统一将数据转为float32格式
image_data = tf.cast(image_data, tf.float32)
return label_data, image_data
(5)主函数运行
if __name__ == '__main__':
#查看CIFAR-10数据是否存在,如果不存在则下载并解压
download()
#将获取的图片保存到这里
image_save_path = './cifar10_image/'
if os.path.exists(image_save_path) == False:
os.mkdir(image_save_path)
#获取图片数据
key, value = get_image('./cifar10_data/cifar-10-batches-bin/')
with tf.Session() as sess:
#初始化变量
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
#这里才真的启动队列
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
for i in range(50):
# print("i:%d" % i)
####################################
#这里data和label不能分开run,否则图片和标签就不匹配了,多谢网友ATPY提醒
#data = sess.run(value)
#label = sess.run(key)
#应该这样
label, data = sess.run([key, value])
####################################
print(label)
scipy.misc.toimage(data).save(image_save_path + '/%d_%d.jpg' % (label, i))
coord.request_stop()
coord.join()
将CIFAR-10数据集中的图片取出来,并保存为.jpg格式。完整代码如下:
#coding: utf-8
# 导入当前目录的cifar10_input,这个模块负责读入cifar10数据
import cifar10_input
# 导入TensorFlow和其他一些可能用到的模块。
import tensorflow as tf
import os
import scipy.misc
def inputs_origin(data_dir):
# filenames一共5个,从data_batch_1.bin到data_batch_5.bin
# 读入的都是训练图像
filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
for i in xrange(1, 6)]
# 判断文件是否存在
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
# 将文件名的list包装成TensorFlow中queue的形式
filename_queue = tf.train.string_input_producer(filenames)
# cifar10_input.read_cifar10是事先写好的从queue中读取文件的函数
# 返回的结果read_input的属性uint8image就是图像的Tensor
read_input = cifar10_input.read_cifar10(filename_queue)
# 将图片转换为实数形式
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
# 返回的reshaped_image是一张图片的tensor
# 我们应当这样理解reshaped_image:每次使用sess.run(reshaped_image),就会取出一张图片
return reshaped_image
if __name__ == '__main__':
# 创建一个会话sess
with tf.Session() as sess:
# 调用inputs_origin。cifar10_data/cifar-10-batches-bin是我们下载的数据的文件夹位置
reshaped_image = inputs_origin('cifar10_data/cifar-10-batches-bin')
# 这一步start_queue_runner很重要。
# 我们之前有filename_queue = tf.train.string_input_producer(filenames)
# 这个queue必须通过start_queue_runners才能启动
# 缺少start_queue_runners程序将不能执行
threads = tf.train.start_queue_runners(sess=sess)
# 变量初始化
sess.run(tf.global_variables_initializer())
# 创建文件夹cifar10_data/raw/
if not os.path.exists('cifar10_data/raw/'):
os.makedirs('cifar10_data/raw/')
# 保存30张图片
for i in range(30):
# 每次sess.run(reshaped_image),都会取出一张图片
image_array = sess.run(reshaped_image)
# 将图片保存
scipy.misc.toimage(image_array).save('cifar10_data/raw/%d.jpg' % i)
4、数据增强
(1)为什么要进行数据增强
深度学习通常要求拥有足够的训练样本。一般而言,数据的总量越多,训练得到的模型效果越好。数据增强可以提高模型的泛化能力,避免过拟合。
(2)如何进行数据增强
在图像处理任务中,可以通过对图像进行一些简单的平移、缩放、颜色变换、旋转、翻转、噪声扰动等均不会改变图像本身的性质,可以作为数据增强的手段。
(3)Tensorflow中的数据增强代码实现:
①使用函数tf.random_crop()对reshaped_image进行随机剪裁。原始的CIFAR-10数据集图像的尺寸是3232,随机剪裁出来的图像块是2424用于训练。因为图像小块可以取在图像的任何位置,所以可以进一步加大训练集的样本数目。
②对剪裁后的图像小块进行水平翻转,每张图片有50%的概率被水平翻转,还有50%的概率保持不变。
③最后对得到的图片进行亮度和对比度的随机改变。
代码如下所示:
# Randomly crop a [height, width] section of the image.
distorted_image = tf.random_crop(reshaped_image, [height, width, 3])
# Randomly flip the image horizontally.
distorted_image = tf.image.random_flip_left_right(distorted_image)
# Because these operations are not commutative, consider randomizing
# the order their operation.
distorted_image = tf.image.random_brightness(distorted_image,
max_delta=63)
distorted_image = tf.image.random_contrast(distorted_image,
lower=0.2, upper=1.8)
完整代码cifar_input.py
# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Routine for decoding the CIFAR-10 binary file format."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
# Process images of this size. Note that this differs from the original CIFAR
# image size of 32 x 32. If one alters this number, then the entire model
# architecture will change and any model would need to be retrained.
IMAGE_SIZE = 24
# Global constants describing the CIFAR-10 data set.
NUM_CLASSES = 10
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 50000
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = 10000
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def _generate_image_and_label_batch(image, label, min_queue_examples,
batch_size, shuffle):
"""Construct a queued batch of images and labels.
Args:
image: 3-D Tensor of [height, width, 3] of type.float32.
label: 1-D Tensor of type.int32
min_queue_examples: int32, minimum number of samples to retain
in the queue that provides of batches of examples.
batch_size: Number of images per batch.
shuffle: boolean indicating whether to use a shuffling queue.
Returns:
images: Images. 4D tensor of [batch_size, height, width, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
# Create a queue that shuffles the examples, and then
# read 'batch_size' images + labels from the example queue.
num_preprocess_threads = 16
if shuffle:
images, label_batch = tf.train.shuffle_batch(
[image, label],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + 3 * batch_size,
min_after_dequeue=min_queue_examples)
else:
images, label_batch = tf.train.batch(
[image, label],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + 3 * batch_size)
# Display the training images in the visualizer.
tf.summary.image('images', images)
return images, tf.reshape(label_batch, [batch_size])
def distorted_inputs(data_dir, batch_size):
"""Construct distorted input for CIFAR training using the Reader ops.
Args:
data_dir: Path to the CIFAR-10 data directory.
batch_size: Number of images per batch.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
for i in xrange(1, 6)]
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
# Create a queue that produces the filenames to read.
filename_queue = tf.train.string_input_producer(filenames)
# Read examples from files in the filename queue.
read_input = read_cifar10(filename_queue)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
# Image processing for training the network. Note the many random
# distortions applied to the image.
# Randomly crop a [height, width] section of the image.
distorted_image = tf.random_crop(reshaped_image, [height, width, 3])
# Randomly flip the image horizontally.
distorted_image = tf.image.random_flip_left_right(distorted_image)
# Because these operations are not commutative, consider randomizing
# the order their operation.
distorted_image = tf.image.random_brightness(distorted_image,
max_delta=63)
distorted_image = tf.image.random_contrast(distorted_image,
lower=0.2, upper=1.8)
# Subtract off the mean and divide by the variance of the pixels.
float_image = tf.image.per_image_standardization(distorted_image)
# Set the shapes of tensors.
float_image.set_shape([height, width, 3])
read_input.label.set_shape([1])
# Ensure that the random shuffling has good mixing properties.
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN *
min_fraction_of_examples_in_queue)
print('Filling queue with %d CIFAR images before starting to train. '
'This will take a few minutes.' % min_queue_examples)
# Generate a batch of images and labels by building up a queue of examples.
return _generate_image_and_label_batch(float_image, read_input.label,
min_queue_examples, batch_size,
shuffle=True)
def inputs(eval_data, data_dir, batch_size):
"""Construct input for CIFAR evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
data_dir: Path to the CIFAR-10 data directory.
batch_size: Number of images per batch.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
if not eval_data:
filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
for i in xrange(1, 6)]
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
else:
filenames = [os.path.join(data_dir, 'test_batch.bin')]
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
# Create a queue that produces the filenames to read.
filename_queue = tf.train.string_input_producer(filenames)
# Read examples from files in the filename queue.
read_input = read_cifar10(filename_queue)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
# Image processing for evaluation.
# Crop the central [height, width] of the image.
resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
height, width)
# Subtract off the mean and divide by the variance of the pixels.
float_image = tf.image.per_image_standardization(resized_image)
# Set the shapes of tensors.
float_image.set_shape([height, width, 3])
read_input.label.set_shape([1])
# Ensure that the random shuffling has good mixing properties.
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(num_examples_per_epoch *
min_fraction_of_examples_in_queue)
# Generate a batch of images and labels by building up a queue of examples.
return _generate_image_and_label_batch(float_image, read_input.label,
min_queue_examples, batch_size,
shuffle=False)
当然,我们也能自己写一个数据增强的代码:
#encoding:utf-8
import tensorflow as tf
import matplotlib.pyplot as plt
#读取原始图像数据
image_data = tf.gfile.FastGFile('qiaoba.jpg', 'r').read()
with tf.Session() as sess:
#对图像使用jpg格式解码,得到三维数据
pltdata = tf.image.decode_jpeg(image_data)
#显示图像
plt.imshow(pltdata.eval())
plt.show()
5、CIFAR-10识别模型
将数据增强后的图像建立一个模型进行识别,代码保存在cifar10.py文件的Inferce()函数中。
def inference(images):
"""Build the CIFAR-10 model.
Args:
images: Images returned from distorted_inputs() or inputs().
Returns:
Logits.
"""
# We instantiate all variables using tf.get_variable() instead of
# tf.Variable() in order to share variables across multiple GPU training runs.
# If we only ran this model on a single GPU, we could simplify this function
# by replacing all instances of tf.get_variable() with tf.Variable().
#
# conv1
with tf.variable_scope('conv1') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[5, 5, 3, 64],
stddev=5e-2,
wd=0.0)
conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.0))
pre_activation = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(pre_activation, name=scope.name)
_activation_summary(conv1)
# pool1
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
padding='SAME', name='pool1')
# norm1
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm1')
# conv2
with tf.variable_scope('conv2') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[5, 5, 64, 64],
stddev=5e-2,
wd=0.0)
conv = tf.nn.conv2d(norm1, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.1))
pre_activation = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(pre_activation, name=scope.name)
_activation_summary(conv2)
# norm2
norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm2')
# pool2
pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1], padding='SAME', name='pool2')
# local3
with tf.variable_scope('local3') as scope:
# Move everything into depth so we can perform a single matrix multiply.
reshape = tf.reshape(pool2, [FLAGS.batch_size, -1])
dim = reshape.get_shape()[1].value
weights = _variable_with_weight_decay('weights', shape=[dim, 384],
stddev=0.04, wd=0.004)
biases = _variable_on_cpu('biases', [384], tf.constant_initializer(0.1))
local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
_activation_summary(local3)
# local4
with tf.variable_scope('local4') as scope:
weights = _variable_with_weight_decay('weights', shape=[384, 192],
stddev=0.04, wd=0.004)
biases = _variable_on_cpu('biases', [192], tf.constant_initializer(0.1))
local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name=scope.name)
_activation_summary(local4)
# linear layer(WX + b),
# We don't apply softmax here because
# tf.nn.sparse_softmax_cross_entropy_with_logits accepts the unscaled logits
# and performs the softmax internally for efficiency.
with tf.variable_scope('softmax_linear') as scope:
weights = _variable_with_weight_decay('weights', [192, NUM_CLASSES],
stddev=1/192.0, wd=0.0)
biases = _variable_on_cpu('biases', [NUM_CLASSES],
tf.constant_initializer(0.0))
softmax_linear = tf.add(tf.matmul(local4, weights), biases, name=scope.name)
_activation_summary(softmax_linear)
return softmax_linear
完整代码如下所示:
# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Builds the CIFAR-10 network.
Summary of available functions:
# Compute input images and labels for training. If you would like to run
# evaluations, use inputs() instead.
inputs, labels = distorted_inputs()
# Compute inference on the model inputs to make a prediction.
predictions = inference(inputs)
# Compute the total loss of the prediction with respect to the labels.
loss = loss(predictions, labels)
# Create a graph to run one step of training with respect to the loss.
train_op = train(loss, global_step)
"""
# pylint: disable=missing-docstring
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import re
import sys
import tarfile
from six.moves import urllib
import tensorflow as tf
import cifar10_input
FLAGS = tf.app.flags.FLAGS
# Basic model parameters.
tf.app.flags.DEFINE_integer('batch_size', 128,
"""Number of images to process in a batch.""")
tf.app.flags.DEFINE_string('data_dir', '/tmp/cifar10_data',
"""Path to the CIFAR-10 data directory.""")
tf.app.flags.DEFINE_boolean('use_fp16', False,
"""Train the model using fp16.""")
# Global constants describing the CIFAR-10 data set.
IMAGE_SIZE = cifar10_input.IMAGE_SIZE
NUM_CLASSES = cifar10_input.NUM_CLASSES
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = cifar10_input.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = cifar10_input.NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
# Constants describing the training process.
MOVING_AVERAGE_DECAY = 0.9999 # The decay to use for the moving average.
NUM_EPOCHS_PER_DECAY = 350.0 # Epochs after which learning rate decays.
LEARNING_RATE_DECAY_FACTOR = 0.1 # Learning rate decay factor.
INITIAL_LEARNING_RATE = 0.1 # Initial learning rate.
# If a model is trained with multiple GPUs, prefix all Op names with tower_name
# to differentiate the operations. Note that this prefix is removed from the
# names of the summaries when visualizing a model.
TOWER_NAME = 'tower'
DATA_URL = 'http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz'
def _activation_summary(x):
"""Helper to create summaries for activations.
Creates a summary that provides a histogram of activations.
Creates a summary that measures the sparsity of activations.
Args:
x: Tensor
Returns:
nothing
"""
# Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
# session. This helps the clarity of presentation on tensorboard.
tensor_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', x.op.name)
tf.summary.histogram(tensor_name + '/activations', x)
tf.summary.scalar(tensor_name + '/sparsity',
tf.nn.zero_fraction(x))
def _variable_on_cpu(name, shape, initializer):
"""Helper to create a Variable stored on CPU memory.
Args:
name: name of the variable
shape: list of ints
initializer: initializer for Variable
Returns:
Variable Tensor
"""
with tf.device('/cpu:0'):
dtype = tf.float16 if FLAGS.use_fp16 else tf.float32
var = tf.get_variable(name, shape, initializer=initializer, dtype=dtype)
return var
def _variable_with_weight_decay(name, shape, stddev, wd):
"""Helper to create an initialized Variable with weight decay.
Note that the Variable is initialized with a truncated normal distribution.
A weight decay is added only if one is specified.
Args:
name: name of the variable
shape: list of ints
stddev: standard deviation of a truncated Gaussian
wd: add L2Loss weight decay multiplied by this float. If None, weight
decay is not added for this Variable.
Returns:
Variable Tensor
"""
dtype = tf.float16 if FLAGS.use_fp16 else tf.float32
var = _variable_on_cpu(
name,
shape,
tf.truncated_normal_initializer(stddev=stddev, dtype=dtype))
if wd is not None:
weight_decay = tf.multiply(tf.nn.l2_loss(var), wd, name='weight_loss')
tf.add_to_collection('losses', weight_decay)
return var
def distorted_inputs():
"""Construct distorted input for CIFAR training using the Reader ops.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
Raises:
ValueError: If no data_dir
"""
if not FLAGS.data_dir:
raise ValueError('Please supply a data_dir')
data_dir = os.path.join(FLAGS.data_dir, 'cifar-10-batches-bin')
images, labels = cifar10_input.distorted_inputs(data_dir=data_dir,
batch_size=FLAGS.batch_size)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels
def inputs(eval_data):
"""Construct input for CIFAR evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
Raises:
ValueError: If no data_dir
"""
if not FLAGS.data_dir:
raise ValueError('Please supply a data_dir')
data_dir = os.path.join(FLAGS.data_dir, 'cifar-10-batches-bin')
images, labels = cifar10_input.inputs(eval_data=eval_data,
data_dir=data_dir,
batch_size=FLAGS.batch_size)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels
def inference(images):
"""Build the CIFAR-10 model.
Args:
images: Images returned from distorted_inputs() or inputs().
Returns:
Logits.
"""
# We instantiate all variables using tf.get_variable() instead of
# tf.Variable() in order to share variables across multiple GPU training runs.
# If we only ran this model on a single GPU, we could simplify this function
# by replacing all instances of tf.get_variable() with tf.Variable().
#
# conv1
with tf.variable_scope('conv1') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[5, 5, 3, 64],
stddev=5e-2,
wd=0.0)
conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.0))
pre_activation = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(pre_activation, name=scope.name)
_activation_summary(conv1)
# pool1
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
padding='SAME', name='pool1')
# norm1
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm1')
# conv2
with tf.variable_scope('conv2') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[5, 5, 64, 64],
stddev=5e-2,
wd=0.0)
conv = tf.nn.conv2d(norm1, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.1))
pre_activation = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(pre_activation, name=scope.name)
_activation_summary(conv2)
# norm2
norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm2')
# pool2
pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1], padding='SAME', name='pool2')
# local3
with tf.variable_scope('local3') as scope:
# Move everything into depth so we can perform a single matrix multiply.
reshape = tf.reshape(pool2, [FLAGS.batch_size, -1])
dim = reshape.get_shape()[1].value
weights = _variable_with_weight_decay('weights', shape=[dim, 384],
stddev=0.04, wd=0.004)
biases = _variable_on_cpu('biases', [384], tf.constant_initializer(0.1))
local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
_activation_summary(local3)
# local4
with tf.variable_scope('local4') as scope:
weights = _variable_with_weight_decay('weights', shape=[384, 192],
stddev=0.04, wd=0.004)
biases = _variable_on_cpu('biases', [192], tf.constant_initializer(0.1))
local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name=scope.name)
_activation_summary(local4)
# linear layer(WX + b),
# We don't apply softmax here because
# tf.nn.sparse_softmax_cross_entropy_with_logits accepts the unscaled logits
# and performs the softmax internally for efficiency.
with tf.variable_scope('softmax_linear') as scope:
weights = _variable_with_weight_decay('weights', [192, NUM_CLASSES],
stddev=1/192.0, wd=0.0)
biases = _variable_on_cpu('biases', [NUM_CLASSES],
tf.constant_initializer(0.0))
softmax_linear = tf.add(tf.matmul(local4, weights), biases, name=scope.name)
_activation_summary(softmax_linear)
return softmax_linear
def loss(logits, labels):
"""Add L2Loss to all the trainable variables.
Add summary for "Loss" and "Loss/avg".
Args:
logits: Logits from inference().
labels: Labels from distorted_inputs or inputs(). 1-D tensor
of shape [batch_size]
Returns:
Loss tensor of type float.
"""
# Calculate the average cross entropy loss across the batch.
labels = tf.cast(labels, tf.int64)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=labels, logits=logits, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
# The total loss is defined as the cross entropy loss plus all of the weight
# decay terms (L2 loss).
return tf.add_n(tf.get_collection('losses'), name='total_loss')
def _add_loss_summaries(total_loss):
"""Add summaries for losses in CIFAR-10 model.
Generates moving average for all losses and associated summaries for
visualizing the performance of the network.
Args:
total_loss: Total loss from loss().
Returns:
loss_averages_op: op for generating moving averages of losses.
"""
# Compute the moving average of all individual losses and the total loss.
loss_averages = tf.train.ExponentialMovingAverage(0.9, name='avg')
losses = tf.get_collection('losses')
loss_averages_op = loss_averages.apply(losses + [total_loss])
# Attach a scalar summary to all individual losses and the total loss; do the
# same for the averaged version of the losses.
for l in losses + [total_loss]:
# Name each loss as '(raw)' and name the moving average version of the loss
# as the original loss name.
tf.summary.scalar(l.op.name + ' (raw)', l)
tf.summary.scalar(l.op.name, loss_averages.average(l))
return loss_averages_op
def train(total_loss, global_step):
"""Train CIFAR-10 model.
Create an optimizer and apply to all trainable variables. Add moving
average for all trainable variables.
Args:
total_loss: Total loss from loss().
global_step: Integer Variable counting the number of training steps
processed.
Returns:
train_op: op for training.
"""
# Variables that affect learning rate.
num_batches_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN / FLAGS.batch_size
decay_steps = int(num_batches_per_epoch * NUM_EPOCHS_PER_DECAY)
# Decay the learning rate exponentially based on the number of steps.
lr = tf.train.exponential_decay(INITIAL_LEARNING_RATE,
global_step,
decay_steps,
LEARNING_RATE_DECAY_FACTOR,
staircase=True)
tf.summary.scalar('learning_rate', lr)
# Generate moving averages of all losses and associated summaries.
loss_averages_op = _add_loss_summaries(total_loss)
# Compute gradients.
with tf.control_dependencies([loss_averages_op]):
opt = tf.train.GradientDescentOptimizer(lr)
grads = opt.compute_gradients(total_loss)
# Apply gradients.
apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
# Add histograms for trainable variables.
for var in tf.trainable_variables():
tf.summary.histogram(var.op.name, var)
# Add histograms for gradients.
for grad, var in grads:
if grad is not None:
tf.summary.histogram(var.op.name + '/gradients', grad)
# Track the moving averages of all trainable variables.
variable_averages = tf.train.ExponentialMovingAverage(
MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
with tf.control_dependencies([apply_gradient_op, variables_averages_op]):
train_op = tf.no_op(name='train')
return train_op
def maybe_download_and_extract():
"""Download and extract the tarball from Alex's website."""
dest_directory = FLAGS.data_dir
if not os.path.exists(dest_directory):
os.makedirs(dest_directory)
filename = DATA_URL.split('/')[-1]
filepath = os.path.join(dest_directory, filename)
if not os.path.exists(filepath):
def _progress(count, block_size, total_size):
sys.stdout.write('\r>> Downloading %s %.1f%%' % (filename,
float(count * block_size) / float(total_size) * 100.0))
sys.stdout.flush()
filepath, _ = urllib.request.urlretrieve(DATA_URL, filepath, _progress)
print()
statinfo = os.stat(filepath)
print('Successfully downloaded', filename, statinfo.st_size, 'bytes.')
extracted_dir_path = os.path.join(dest_directory, 'cifar-10-batches-bin')
if not os.path.exists(extracted_dir_path):
tarfile.open(filepath, 'r:gz').extractall(dest_directory)
6、使用tensorboard进行可视化
在进行模型训练的时候,我们需要对训练的情况进行可视化,从而实现实时监控训练过程的目的。
在命令窗口可以输入:
tensorboard --logdir cifar10_train/
tensorboard 默认在6060端口进行运行,复制粘贴地址链接即可进入tensorboard 的主页面。
完整代码:
# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""A binary to train CIFAR-10 using a single GPU.
Accuracy:
cifar10_train.py achieves ~86% accuracy after 100K steps (256 epochs of
data) as judged by cifar10_eval.py.
Speed: With batch_size 128.
System | Step Time (sec/batch) | Accuracy
------------------------------------------------------------------
1 Tesla K20m | 0.35-0.60 | ~86% at 60K steps (5 hours)
1 Tesla K40m | 0.25-0.35 | ~86% at 100K steps (4 hours)
Usage:
Please see the tutorial and website for how to download the CIFAR-10
data set, compile the program and train the model.
http://tensorflow.org/tutorials/deep_cnn/
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from datetime import datetime
import time
import tensorflow as tf
import cifar10
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string('train_dir', '/tmp/cifar10_train',
"""Directory where to write event logs """
"""and checkpoint.""")
tf.app.flags.DEFINE_integer('max_steps', 1000000,
"""Number of batches to run.""")
tf.app.flags.DEFINE_boolean('log_device_placement', False,
"""Whether to log device placement.""")
tf.app.flags.DEFINE_integer('log_frequency', 10,
"""How often to log results to the console.""")
def train():
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.contrib.framework.get_or_create_global_step()
# Get images and labels for CIFAR-10.
images, labels = cifar10.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = cifar10.inference(images)
# Calculate loss.
loss = cifar10.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = cifar10.train(loss, global_step)
class _LoggerHook(tf.train.SessionRunHook):
"""Logs loss and runtime."""
def begin(self):
self._step = -1
self._start_time = time.time()
def before_run(self, run_context):
self._step += 1
return tf.train.SessionRunArgs(loss) # Asks for loss value.
def after_run(self, run_context, run_values):
if self._step % FLAGS.log_frequency == 0:
current_time = time.time()
duration = current_time - self._start_time
self._start_time = current_time
loss_value = run_values.results
examples_per_sec = FLAGS.log_frequency * FLAGS.batch_size / duration
sec_per_batch = float(duration / FLAGS.log_frequency)
format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print(format_str % (datetime.now(), self._step, loss_value,
examples_per_sec, sec_per_batch))
with tf.train.MonitoredTrainingSession(
checkpoint_dir=FLAGS.train_dir,
hooks=[tf.train.StopAtStepHook(last_step=FLAGS.max_steps),
tf.train.NanTensorHook(loss),
_LoggerHook()],
config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement)) as mon_sess:
while not mon_sess.should_stop():
mon_sess.run(train_op)
def main(argv=None): # pylint: disable=unused-argument
cifar10.maybe_download_and_extract()
if tf.gfile.Exists(FLAGS.train_dir):
tf.gfile.DeleteRecursively(FLAGS.train_dir)
tf.gfile.MakeDirs(FLAGS.train_dir)
train()
if __name__ == '__main__':
tf.app.run()
作业:
(1)下载ImageNet数据集,进行调参提高准确率
(2)对上一期作业进行网络调参,提高准确率
(3)继续学习tensorflow视频课程(P15-P20)https://www.bilibili.com/video/av20542427?from=search&seid=8546039398255828905
参考文献:
(1)https://blog.csdn.net/rookie_wei/article/details/80187950
(2)https://blog.csdn.net/rookie_wei/article/details/80409240
(3)https://blog.csdn.net/rookie_wei/article/details/80409401