# tensorflow之CNN進階cifar10實現

1.下載tensorflow models庫，在終端進行操作

``````sudo apt install git #安裝git，若有則無需安裝
git clone https://github.com/tensorflow/models.git
cd models/tutorials/image/cifar10``````

2.載入需要的庫，在.py檔案中操作

``````import cifar10
import cifar10_input
import tensorflow as tf
import numpy as np
import time ``````

3.定義迭代引數

``````max_steps = 3000 #最大迭代次數
batch_size = 128
data_dir = '/home/chunmei/tmp/cifar10_data/cifar-10-batches-bin'#檔案下載解壓後的路徑``````

4.定義初始化權值函式

``````def variable_with_weight_loss(shape, stddev, w1):
var = tf.Variable(tf.truncated_normal(shape, stddev=stddev))#截斷到正態分佈來初始化權重
if w1 is not None:
#w1控制L2正則化的大小
weight_loss = tf.multiply(tf.nn.l2_loss(var), w1, name='weight_loss')#L2正則化權值後再和w1相乘，用w1控制L2loss
return var``````

5.使用cifar10下載資料集並解壓展開到預設位置。

``````cifar10.maybe_download_and_extract()#下載資料集
#訓練集
images_train, labels_train = cifar10_input.distorted_inputs(data_dir=data_dir, batch_size=batch_size)
#cifar10_input類中帶的distorted_inputs()函式可以產生訓練需要的資料，包括特徵和label，返回封裝好的tensor，每次執行都會生成一個batch_size大小的資料。
#測試集
images_test, labels_test = cifar10_input.inputs(eval_data = True, data_dir=data_dir, batch_size=batch_size)``````

tf.image.per_image_whitening，對資料減去均值，除以方差，保證資料均值為0，方差為1。
6.輸入資料

``````image_in = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])#裁剪後尺寸為24×24，彩色影象通道數為3
label_in = tf.placeholder(tf.float32, [batch_size])``````

7.第一個卷積層

``````weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64],stddev=5e-2, w1=0.0)#5×5的卷積和，3個通道，64個濾波器
kernel1 = tf.nn.conv2d(image_in, weight1, strides=[1, 1, 1, 1], padding = 'SAME')#卷積1
bias1 = tf.Variable(tf.constant(0.0, shape=[64]))
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)``````

8.第二個卷積層

``````weight2 = variable_with_weight_loss(shape=[5, 5, 64, 64],stddev=5e-2, w1=0.0)#5×5的卷積和，第一個卷積層輸出64個通道，64個濾波器
kernel2 = tf.nn.conv2d(norm1, weight2, strides=[1, 1, 1, 1], padding = 'SAME')#卷積1
bias2 = tf.Variable(tf.constant(0.1, shape=[64]))#此處bias初始化為0.1
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？``````

9.全連線層1

``````reshape = tf.reshape(pool2, [batch_size, -1])#將資料變為1D資料
dim = reshape.get_shape()[1].value#獲取維度
weight3 = variable_with_weight_loss(shape=[dim, 384], stddev=0.04, w1=0.004)
bias3 = tf.Variable(tf.constant(0.1, shape=[384]))#此處bias初始化為0.1
local3 = tf.nn.relu(tf.matmul(reshape,  weight3)   bias3))``````

10.全連線層2

``````weight4 = variable_with_weight_loss(shape=[384, 192], stddev=0.04, w1=0.004)
bias4 = tf.Variable(tf.constant(0.1, shape=[192]))#此處bias初始化為0.1
local4 = tf.nn.relu(tf.matmul(local3,  weight4)   bia4))``````

11.最後一層

``````weight5 = variable_with_weight_loss(shape=[192, 10], stddev=1/199.0, w1=0.0)
bias5 = tf.Variable(tf.constant(0.0, shape=[10]))

12.網路結構

layer名稱描述
conv1卷積層和ReLU
pool1最大池化
norm1LRN
conv2卷積層和ReLU
norm2LRN
pool2最大池化
local3全連線層和ReLU
local4全連線層和ReLU
logits模型的inference的輸出結果

13.計算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的計算合在一起
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
#計算cross entropy 均值
#將整體losses的collection中的全部loss求和，得到最終的loss，其中包括cross entropy loss，還有後兩個全連線層中weight的L2 loss

14.資料準備

``````loss = loss(logits, labels_i)  #傳遞誤差和labels
top_k_op = tf.nn.in_top_k(logits, label_in, 1) #得分最高的那一類的準確率
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
#初始化變數
tf.train.start_queue_runners()
#啟動執行緒，在影象資料增強佇列例使用了16個執行緒進行加速。``````

15.訓練

``````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))``````

16.測試模型準確率

``````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``````

17.列印準確率

``````precision = true_count / total_sample_count
print('precision @ 1 = %.3f' % precision)``````

18.程式綜合

``````##載入庫
import tensorflow as tf
import time
import numpy as np
import cifar10
import cifar10_input
##定義迭代引數
max_steps = 3000 #最大迭代次數
batch_size = 128
data_dir = '/tmp/cifar10_data/cifar-10-batches-bin'#預設下載路徑/home/zcm/tensorf/test/cifar10/cifar10_data/cifar-10-batches-bin/cifar-10-batches-py
##定義初始化權值函式
def variable_with_weight_loss(shape, stddev, w1):
var = tf.Variable(tf.truncated_normal(shape, stddev=stddev))#截斷到正態分佈來初始化權重
if w1 is not None:
#w1控制L2正則化的大小
weight_loss = tf.multiply(tf.nn.l2_loss(var), w1, name='weight_loss')
#L2正則化權值後再和w1相乘，用w1控制L2loss
#儲存weight_loss到名為'loses'的collection上面
return var
##使用cifar10下載資料集並解壓展開到預設位置
#訓練集
images_train, labels_train = cifar10_input.distorted_inputs(data_dir=data_dir, batch_size=batch_size)
#cifar10_input類中帶的distorted_inputs()函式可以產生訓練需要的資料，包括特徵和label，返回封裝好的tensor，每次執行都會生成一個batch_size大小的資料。
#測試集
images_test, labels_test = cifar10_input.inputs(eval_data = True, data_dir=data_dir, batch_size=batch_size)
##載入資料
image_in = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])#裁剪後尺寸為24×24，彩色影象通道數為3
label_in = tf.placeholder(tf.int32, [batch_size])
##第一個卷積層
weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64],stddev=5e-2,w1=0.0)#5×5的卷積和，3個通道，64個濾波器
kernel1 = tf.nn.conv2d(image_in, weight1, strides=[1, 1, 1, 1], padding = 'SAME')#卷積1
bias1 = tf.Variable(tf.constant(0.0, shape=[64]))
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)
##第二個卷積層
weight2 = variable_with_weight_loss(shape=[5, 5, 64, 64],stddev=5e-2,w1=0.0)#5×5的卷積和，第一個卷積層輸出64個通道，64個濾波器
kernel2 = tf.nn.conv2d(norm1, weight2, strides=[1, 1, 1, 1], padding = 'SAME')#卷積1
bias2 = tf.Variable(tf.constant(0.1, shape=[64]))#此處bias初始化為0.1
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)
##全連線層1
reshape = tf.reshape(pool2, [batch_size, -1])#將資料變為1D資料
dim = reshape.get_shape()[1].value#獲取維度
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]))#此處bias初始化為0.1
local3 = tf.nn.relu(tf.matmul(reshape,weight3) bias3)
##全連線層2
weight4 = variable_with_weight_loss(shape=[384, 192], stddev=0.04, w1=0.004)
bias4 = tf.Variable(tf.constant(0.1, shape=[192]))#此處bias初始化為0.1
local4 = tf.nn.relu(tf.matmul(local3,  weight4)   bias4)
##最後一層
weight5 = variable_with_weight_loss(shape=[192, 10], stddev=1/199.0, w1=0.0)
bias5 = tf.Variable(tf.constant(0.0, shape=[10]))
##計算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的計算合在一起
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
#計算cross entropy 均值
#將整體losses的collection中的全部loss求和，得到最終的loss，其中包括cross entropy loss，還有後兩個全連線層中weight的L2 loss
##資料準備
loss = loss(logits, label_in)  #傳遞誤差和label
top_k_op = tf.nn.in_top_k(logits, label_in, 1) #得分最高的那一類的準確率
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
#初始化變數
tf.train.start_queue_runners()
#啟動執行緒，在影象資料增強佇列例使用了16個執行緒進行加速。
##訓練
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 #執行時間
if step %10 == 0:
example_per_sec = batch_size/duration#每秒訓練樣本數
sec_per_batch = float(duration) #每個batch時間
format_str = ('step %d, loss=%.2f(%.1f exaples/sec; %.3f sec/batch)')
print(format_str % (step, loss_value, example_per_sec, sec_per_batch))
##測試模型準確率
num_examples = 1000
import math
num_iter = int(math.ceil(num_examples / batch_size))#math.ceil()為向上取整
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})
##列印準確率
true_count  = np.sum(predictions)
step  =1
precision = true_count / total_sample_count
print('precision @ 1 = %.3f' % precision)``````

19.結論

20.cifar10的python檔案，出現在上述的import,這是我直接在網上下載的，來自於tensorflow的models
(1)cifar10_input.py

``````# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#
# Unless required by applicable law or agreed to in writing, software
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# ==============================================================================
"""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
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
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.
# 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.
if shuffle:
images, label_batch = tf.train.shuffle_batch(
[image, label],
batch_size=batch_size,
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,
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.
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])
# 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.
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.
height = IMAGE_SIZE
width = IMAGE_SIZE
# Image processing for evaluation.
# Crop the central [height, width] of the 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])
# 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.
min_queue_examples, batch_size,
shuffle=False)``````

(2)cifar10.py

``````# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#
# Unless required by applicable law or agreed to in writing, software
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# ==============================================================================
"""Builds the CIFAR-10 network.
Summary of available functions:
# Compute input images and labels for training. If you would like to run
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.
help='Number of images to process in a batch.')
help='Path to the CIFAR-10 data directory.')
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')
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:
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:
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))
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],
# 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))
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')
# The total loss is defined as the cross entropy loss plus all of the weight
# decay terms (L2 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.
with tf.control_dependencies([loss_averages_op]):
# Add histograms for trainable variables.
for var in tf.trainable_variables():
tf.summary.histogram(var.op.name, var)
# 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())
train_op = tf.no_op(name='train')
return train_op
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):