之前一篇文章有写到简单到两层卷积神经网络(http://blog.csdn.net/xuan_zizizi/article/details/77816745)完成mnist手写数据集的识别,正确率达到96%以上。这篇文章将采用经典的CIFAR-10数据集,包含60000张32×32的彩色图像,其中共10类物体,每一类6000张。参看《tensorflow实战》
1.下载tensorflow models库,在终端进行操作
sudo apt install git #安装git,若有则无需安装
git clone https://github.com/tensorflow/models.git
cd models/tutorials/image/cifar10
- 1
- 2
- 3
2.载入需要的库,在.py文件中操作
import cifar10
import cifar10_input
import tensorflow as tf
import numpy as np
import time
- 1
- 2
- 3
- 4
- 5
3.定义迭代参数
max_steps = 3000 #最大迭代次数
batch_size = 128
data_dir = '/home/chunmei/tmp/cifar10_data/cifar-10-batches-bin'#文件下载解压后的路径
- 1
- 2
- 3
4.定义初始化权值函数
def variable_with_weight_loss(shape, stddev, w1):
var = tf.Variable(tf.truncated_normal(shape, stddev=stddev))#截断到正态分布来初始化权重
if w1 is not None:
#w1控制L2正则化的大小
weight_loss = tf.multiply(tf.nn.l2_loss(var), w1, name='weight_loss')#L2正则化权值后再和w1相乘,用w1控制L2loss
tf.add_to_collection('losses',weight_loss)#储存weight_loss到名为'loses'的collection上面
return var
- 1
- 2
- 3
- 4
- 5
- 6
- 7
正则化用于惩罚特征权重,即特征权重为模型损失函数的一部分。一般,L1正则化可以理解为制造稀疏特征,即大部分无用特征被置为0,而L2正则化则是让特征的权重不要过大,使得特征权重较为平均。
5.使用cifar10下载数据集并解压展开到默认位置。
cifar10.maybe_download_and_extract()#下载数据集
#训练集
images_train, labels_train = cifar10_input.distorted_inputs(data_dir=data_dir, batch_size=batch_size)
#cifar10_input类中带的distorted_inputs()函数可以产生训练需要的数据,包括特征和label,返回封装好的tensor,每次执行都会生成一个batch_size大小的数据。
#测试集
images_test, labels_test = cifar10_input.inputs(eval_data = True, data_dir=data_dir, batch_size=batch_size)
- 1
- 2
- 3
- 4
- 5
- 6
数据增强函数cifar10_input.distorted_inputs()的操作包括:
随机的水平旋转(tf.image.random_flip_left_right)
随机剪切一块24×24大小的图片(tf.random_crop)
设置随机的亮度和对比度(tf.image.random_brightness、tf.image.random_contrast)
数据标准化:
tf.image.per_image_whitening,对数据减去均值,除以方差,保证数据均值为0,方差为1。
6.输入数据
image_in = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])#裁剪后尺寸为24×24,彩色图像通道数为3
label_in = tf.placeholder(tf.float32, [batch_size])
- 1
- 2
7.第一个卷积层
首先设置卷积权值,进行卷积,加上偏置,然后进行ReLU非线性处理,然后进行max_pooling,最后加一个LRN(Local Response Nomalization,局部响应归一化),模仿了生物系统的’侧抑制’机制,对局部神经元的活动创建竞争环境,使得相对较大的权值更大,并抑制其他相对较小的神经元,增强模型的泛化能力。
weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64],stddev=5e-2, w1=0.0)#5×5的卷积和,3个通道,64个滤波器
kernel1 = tf.nn.conv2d(image_in, weight1, strides=[1, 1, 1, 1], padding = 'SAME')#卷积1
bias1 = tf.Variable(tf.constant(0.0, shape=[64]))
conv1 = tf.nn.relu(tf.nn.bias_add(kernel1, bias1))
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')#same?尺寸?
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)
- 1
- 2
- 3
- 4
- 5
- 6
8.第二个卷积层
首先设置卷积权值,进行卷积,加上偏置,然后进行ReLU非线性处理,然后进行LRN,最后加一个进行max_pooling。
weight2 = variable_with_weight_loss(shape=[5, 5, 64, 64],stddev=5e-2, w1=0.0)#5×5的卷积和,第一个卷积层输出64个通道,64个滤波器
kernel2 = tf.nn.conv2d(norm1, weight2, strides=[1, 1, 1, 1], padding = 'SAME')#卷积1
bias2 = tf.Variable(tf.constant(0.1, shape=[64]))#此处bias初始化为0.1
conv2 = tf.nn.relu(tf.nn.bias_add(kernel2, bias2))
norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)
pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')#same?尺寸?
- 1
- 2
- 3
- 4
- 5
- 6
9.全连接层1
将第二个卷积层的输出进行flatten,然后输入一个全连接层,全连接层隐含节点为384,然后还是经过一个ReLU非线性处理。
reshape = tf.reshape(pool2, [batch_size, -1])#将数据变为1D数据
dim = reshape.get_shape()[1].value#获取维度
weight3 = variable_with_weight_loss(shape=[dim, 384], stddev=0.04, w1=0.004)
bias3 = tf.Variable(tf.constant(0.1, shape=[384]))#此处bias初始化为0.1
local3 = tf.nn.relu(tf.matmul(reshape, weight3) + bias3))
- 1
- 2
- 3
- 4
- 5
10.全连接层2
weight4 = variable_with_weight_loss(shape=[384, 192], stddev=0.04, w1=0.004)
bias4 = tf.Variable(tf.constant(0.1, shape=[192]))#此处bias初始化为0.1
local4 = tf.nn.relu(tf.matmul(local3, weight4) + bia4))
- 1
- 2
- 3
11.最后一层
weight5 = variable_with_weight_loss(shape=[192, 10], stddev=1/199.0, w1=0.0)
bias5 = tf.Variable(tf.constant(0.0, shape=[10]))
logits = tf.add(tf.matmul(local4, weight5), bias5)
- 1
- 2
- 3
12.网络结构
layer名称 | 描述 |
---|---|
conv1 | 卷积层和ReLU |
pool1 | 最大池化 |
norm1 | LRN |
conv2 | 卷积层和ReLU |
norm2 | LRN |
pool2 | 最大池化 |
local3 | 全连接层和ReLU |
local4 | 全连接层和ReLU |
logits | 模型的inference的输出结果 |
13.计算softmax和loss
def loss(logits, labels):
labels = tf.cast(labels, tf.int64)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=labels, name='cross_entropy_per_example')
#softmax和cross entropy loss的计算合在一起
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
#计算cross entropy 均值
tf.add_to_collection('losses', cross_entropy_mean)
#将整体losses的collection中的全部loss求和,得到最终的loss,其中包括cross entropy loss,还有后两个全连接层中weight的L2 loss
return tf.add_n(tf.get_collection('losses'), name = 'total_loss')
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
14.数据准备
loss = loss(logits, labels_i) #传递误差和labels
train_op = tf.train.AdamOptimizer(1e-3).minimize(loss) #优化器
top_k_op = tf.nn.in_top_k(logits, label_in, 1) #得分最高的那一类的准确率
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
#初始化变量
tf.train.start_queue_runners()
#启动线程,在图像数据增强队列例使用了16个线程进行加速。
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
15.训练
for step in range(max_steps)
start_time = time.time()
image_batch, label_batch = sess.run([images_train, labels_train])
free, loss_value = sess.run([train_op, loss], feed_dict = {image_in: image_batch, label_in: label_batch})
duration = time.time() - start_time
if step %10 == 0:
example_per_sec = batch_size/duration
sec_per_batch = float(duration)
format_str = ('step %d, loss=%.2f(%.1f exaples/sec; %.3f sec/batch)')
print(format_str % (step, loss_value, example_per_sec, sec_per_batch))
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
16.测试模型准确率
num_examples = 1000
import math
num_iter = int(math.ceil(num_examples / batch_size))
true_count = 0
total_sample_count = num_iter * batch_szie
step = 0
while step < num_iter:
image_batch, label_batch = sess.run([images_test, labels_test])
predictions = sess.run([top_k_op],feed_dict={image_in: image_batch, label_in: label_batch})
true_count += np.sum(predictions)
step +=1
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
17.打印准确率
precision = true_count / total_sample_count
print('precision @ 1 = %.3f' % precision)
- 1
- 2
18.程序综合
##载入库
import tensorflow as tf
import time
import numpy as np
import cifar10
import cifar10_input
##定义迭代参数
max_steps = 3000 #最大迭代次数
batch_size = 128
data_dir = '/tmp/cifar10_data/cifar-10-batches-bin'#默认下载路径/home/zcm/tensorf/test/cifar10/cifar10_data/cifar-10-batches-bin/cifar-10-batches-py
##定义初始化权值函数
def variable_with_weight_loss(shape, stddev, w1):
var = tf.Variable(tf.truncated_normal(shape, stddev=stddev))#截断到正态分布来初始化权重
if w1 is not None:
#w1控制L2正则化的大小
weight_loss = tf.multiply(tf.nn.l2_loss(var), w1, name='weight_loss')
#L2正则化权值后再和w1相乘,用w1控制L2loss
tf.add_to_collection('losses',weight_loss)
#储存weight_loss到名为'loses'的collection上面
return var
##使用cifar10下载数据集并解压展开到默认位置
cifar10.maybe_download_and_extract()#下载数据集
#训练集
images_train, labels_train = cifar10_input.distorted_inputs(data_dir=data_dir, batch_size=batch_size)
#cifar10_input类中带的distorted_inputs()函数可以产生训练需要的数据,包括特征和label,返回封装好的tensor,每次执行都会生成一个batch_size大小的数据。
#测试集
images_test, labels_test = cifar10_input.inputs(eval_data = True, data_dir=data_dir, batch_size=batch_size)
##载入数据
image_in = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])#裁剪后尺寸为24×24,彩色图像通道数为3
label_in = tf.placeholder(tf.int32, [batch_size])
##第一个卷积层
weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64],stddev=5e-2,w1=0.0)#5×5的卷积和,3个通道,64个滤波器
kernel1 = tf.nn.conv2d(image_in, weight1, strides=[1, 1, 1, 1], padding = 'SAME')#卷积1
bias1 = tf.Variable(tf.constant(0.0, shape=[64]))
conv1 = tf.nn.relu(tf.nn.bias_add(kernel1, bias1))
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')#same?尺寸?
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)
##第二个卷积层
weight2 = variable_with_weight_loss(shape=[5, 5, 64, 64],stddev=5e-2,w1=0.0)#5×5的卷积和,第一个卷积层输出64个通道,64个滤波器
kernel2 = tf.nn.conv2d(norm1, weight2, strides=[1, 1, 1, 1], padding = 'SAME')#卷积1
bias2 = tf.Variable(tf.constant(0.1, shape=[64]))#此处bias初始化为0.1
conv2 = tf.nn.relu(tf.nn.bias_add(kernel2, bias2))
norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)
pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')#same?尺寸?
print (pool2.shape)
##全连接层1
reshape = tf.reshape(pool2, [batch_size, -1])#将数据变为1D数据
dim = reshape.get_shape()[1].value#获取维度
print (dim)
weight3 = variable_with_weight_loss(shape=[dim, 384], stddev=0.04, w1=0.004)
bias3 = tf.Variable(tf.constant(0.1, shape=[384]))#此处bias初始化为0.1
local3 = tf.nn.relu(tf.matmul(reshape,weight3)+bias3)
##全连接层2
weight4 = variable_with_weight_loss(shape=[384, 192], stddev=0.04, w1=0.004)
bias4 = tf.Variable(tf.constant(0.1, shape=[192]))#此处bias初始化为0.1
local4 = tf.nn.relu(tf.matmul(local3, weight4) + bias4)
##最后一层
weight5 = variable_with_weight_loss(shape=[192, 10], stddev=1/199.0, w1=0.0)
bias5 = tf.Variable(tf.constant(0.0, shape=[10]))
logits = tf.add(tf.matmul(local4, weight5), bias5)
##计算softmax和loss
def loss(logits, labels):
labels = tf.cast(labels, tf.int64)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=labels, name='cross_entropy_per_example')
#softmax和cross entropy loss的计算合在一起
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
#计算cross entropy 均值
tf.add_to_collection('losses', cross_entropy_mean)
#将整体losses的collection中的全部loss求和,得到最终的loss,其中包括cross entropy loss,还有后两个全连接层中weight的L2 loss
return tf.add_n(tf.get_collection('losses'), name = 'total_loss')
##数据准备
loss = loss(logits, label_in) #传递误差和label
train_op = tf.train.AdamOptimizer(1e-3).minimize(loss) #优化器
top_k_op = tf.nn.in_top_k(logits, label_in, 1) #得分最高的那一类的准确率
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
#初始化变量
tf.train.start_queue_runners()
#启动线程,在图像数据增强队列例使用了16个线程进行加速。
##训练
for step in range(max_steps):
start_time = time.time()
image_batch, label_batch = sess.run([images_train, labels_train])
free, loss_value = sess.run([train_op, loss], feed_dict = {image_in: image_batch, label_in: label_batch})
duration = time.time() - start_time #运行时间
if step %10 == 0:
example_per_sec = batch_size/duration#每秒训练样本数
sec_per_batch = float(duration) #每个batch时间
format_str = ('step %d, loss=%.2f(%.1f exaples/sec; %.3f sec/batch)')
print(format_str % (step, loss_value, example_per_sec, sec_per_batch))
##测试模型准确率
num_examples = 1000
import math
num_iter = int(math.ceil(num_examples / batch_size))#math.ceil()为向上取整
true_count = 0
total_sample_count = num_iter * batch_size
step = 0
while step < num_iter:
image_batch, label_batch = sess.run([images_test, labels_test])
predictions = sess.run([top_k_op],feed_dict={image_in: image_batch, label_in: label_batch})
##打印准确率
true_count += np.sum(predictions)
step +=1
precision = true_count / total_sample_count
print('precision @ 1 = %.3f' % precision)
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
- 63
- 64
- 65
- 66
- 67
- 68
- 69
- 70
- 71
- 72
- 73
- 74
- 75
- 76
- 77
- 78
- 79
- 80
- 81
- 82
- 83
- 84
- 85
- 86
- 87
- 88
- 89
- 90
- 91
- 92
- 93
- 94
- 95
- 96
- 97
- 98
- 99
- 100
- 101
- 102
- 103
- 104
- 105
19.结论
在max_steps=3000, batch_size=128时,正确率为73.4% 左右,每次运行结果随机,增加max_steps=5000,batch_size=200,正确率可以达到76.9%。
20.cifar10的python文件,出现在上述的import,这是我直接在网上下载的,来自于tensorflow的models
(1)cifar10_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.
# NOTE: since per_image_standardization zeros the mean and makes
# the stddev unit, this likely has no effect see tensorflow#1458.
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)
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
- 63
- 64
- 65
- 66
- 67
- 68
- 69
- 70
- 71
- 72
- 73
- 74
- 75
- 76
- 77
- 78
- 79
- 80
- 81
- 82
- 83
- 84
- 85
- 86
- 87
- 88
- 89
- 90
- 91
- 92
- 93
- 94
- 95
- 96
- 97
- 98
- 99
- 100
- 101
- 102
- 103
- 104
- 105
- 106
- 107
- 108
- 109
- 110
- 111
- 112
- 113
- 114
- 115
- 116
- 117
- 118
- 119
- 120
- 121
- 122
- 123
- 124
- 125
- 126
- 127
- 128
- 129
- 130
- 131
- 132
- 133
- 134
- 135
- 136
- 137
- 138
- 139
- 140
- 141
- 142
- 143
- 144
- 145
- 146
- 147
- 148
- 149
- 150
- 151
- 152
- 153
- 154
- 155
- 156
- 157
- 158
- 159
- 160
- 161
- 162
- 163
- 164
- 165
- 166
- 167
- 168
- 169
- 170
- 171
- 172
- 173
- 174
- 175
- 176
- 177
- 178
- 179
- 180
- 181
- 182
- 183
- 184
- 185
- 186
- 187
- 188
- 189
- 190
- 191
- 192
- 193
- 194
- 195
- 196
- 197
- 198
- 199
- 200
- 201
- 202
- 203
- 204
- 205
- 206
- 207
- 208
- 209
- 210
- 211
- 212
- 213
- 214
- 215
- 216
- 217
- 218
- 219
- 220
- 221
- 222
- 223
- 224
- 225
- 226
- 227
- 228
- 229
- 230
- 231
- 232
- 233
- 234
- 235
- 236
- 237
- 238
- 239
- 240
- 241
- 242
- 243
- 244
- 245
- 246
- 247
- 248
- 249
- 250
- 251
- 252
- 253
- 254
(2)cifar10.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.
# ==============================================================================
"""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 argparse
import os
import re
import sys
import tarfile
from six.moves import urllib
import tensorflow as tf
import cifar10_input
parser = argparse.ArgumentParser()
# Basic model parameters.
parser.add_argument('--batch_size', type=int, default=128,
help='Number of images to process in a batch.')
parser.add_argument('--data_dir', type=str, default='/tmp/cifar10_data',
help='Path to the CIFAR-10 data directory.')
parser.add_argument('--use_fp16', type=bool, default=False,
help='Train the model using fp16.')
FLAGS = parser.parse_args()
# 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)
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
- 58
- 59
- 60
- 61
- 62
- 63
- 64
- 65
- 66
- 67
- 68
- 69
- 70
- 71
- 72
- 73
- 74
- 75
- 76
- 77
- 78
- 79
- 80
- 81
- 82
- 83
- 84
- 85
- 86
- 87
- 88
- 89
- 90
- 91
- 92
- 93
- 94
- 95
- 96
- 97
- 98
- 99
- 100
- 101
- 102
- 103
- 104
- 105
- 106
- 107
- 108
- 109
- 110
- 111
- 112
- 113
- 114
- 115
- 116
- 117
- 118
- 119
- 120
- 121
- 122
- 123
- 124
- 125
- 126
- 127
- 128
- 129
- 130
- 131
- 132
- 133
- 134
- 135
- 136
- 137
- 138
- 139
- 140
- 141
- 142
- 143
- 144
- 145
- 146
- 147
- 148
- 149
- 150
- 151
- 152
- 153
- 154
- 155
- 156
- 157
- 158
- 159
- 160
- 161
- 162
- 163
- 164
- 165
- 166
- 167
- 168
- 169
- 170
- 171
- 172
- 173
- 174
- 175
- 176
- 177
- 178
- 179
- 180
- 181
- 182
- 183
- 184
- 185
- 186
- 187
- 188
- 189
- 190
- 191
- 192
- 193
- 194
- 195
- 196
- 197
- 198
- 199
- 200
- 201
- 202
- 203
- 204
- 205
- 206
- 207
- 208
- 209
- 210
- 211
- 212
- 213
- 214
- 215
- 216
- 217
- 218
- 219
- 220
- 221
- 222
- 223
- 224
- 225
- 226
- 227
- 228
- 229
- 230
- 231
- 232
- 233
- 234
- 235
- 236
- 237
- 238
- 239
- 240
- 241
- 242
- 243
- 244
- 245
- 246
- 247
- 248
- 249
- 250
- 251
- 252
- 253
- 254
- 255
- 256
- 257
- 258
- 259
- 260
- 261
- 262
- 263
- 264
- 265
- 266
- 267
- 268
- 269
- 270
- 271
- 272
- 273
- 274
- 275
- 276
- 277
- 278
- 279
- 280
- 281
- 282
- 283
- 284
- 285
- 286
- 287
- 288
- 289
- 290
- 291
- 292
- 293
- 294
- 295
- 296
- 297
- 298
- 299
- 300
- 301
- 302
- 303
- 304
- 305
- 306
- 307
- 308
- 309
- 310
- 311
- 312
- 313
- 314
- 315
- 316
- 317
- 318
- 319
- 320
- 321
- 322
- 323
- 324
- 325
- 326
- 327
- 328
- 329
- 330
- 331
- 332
- 333
- 334
- 335
- 336
- 337
- 338
- 339
- 340
- 341
- 342
- 343
- 344
- 345
- 346
- 347
- 348
- 349
- 350
- 351
- 352
- 353
- 354
- 355
- 356
- 357
- 358
- 359
- 360
- 361
- 362
- 363
- 364
- 365
- 366
- 367
- 368
- 369
- 370
- 371
- 372
- 373
- 374
- 375
- 376
- 377
- 378
- 379
- 380
- 381
- 382
- 383
- 384
- 385
- 386
- 387
- 388
- 389
- 390
- 391
- 392
- 393
- 394
- 395
- 396
- 397
- 398
- 399
- 400
- 401
- 402
- 403
<link href="https://csdnimg.cn/release/phoenix/mdeditor/markdown_views-a47e74522c.css" rel="stylesheet">
</div>