深度學習之TensorFlow使用CNN測試Cifar-10資料集(Python實現)
題目描述:
1. 對Cifar-10影象資料集,用卷積神經網路進行分類,統計正確率。
2.選用Caffe, Tensorflow, Pytorch等開 源深度學習框架之一,學會安裝這些框架並呼叫它們的介面。
3.直接採用這些深度學習框架針對Cifar-10資料集已訓練好的網路模型,只做測試。
實現流程:
第一步:安裝Tensorflow環境。開啟命令控制符視窗,使用python自帶的pip工具,輸入命令:pip install tensorflow進行下載安裝如圖1 所示:
圖 1
第二步:下載Cifar-10影象資料集。
(官網上下載即可http://www.cs.toronto.edu/~kriz/cifar.html)如圖2所示
圖 2下載Cifar-10
第三步:編寫程式碼,進行訓練測試。
首先,對Cifar-10影象資料集進行介紹。這是一個經典的資料集,包含了60000張32*32的彩色影象,其中訓練集50000張,測試集10000張,如同其名字,CIFAR-10資料集一共標註為10類,每一類6000張圖片,這10類分別是airplane、automobile、bird、cat、deer、dog、frog、horse、ship和truck。類別之間沒有重疊,也不會一張圖片中出現兩類物體。
然後,建立卷積神經網路模型CNN。並且新增一些新功能:
(1)對權重weights進行L2正則化;
(2)對圖片資料進行資料增強,即對圖片進行翻轉、隨機剪下等操作,製造了更多的樣本;
(3)在每個卷積-池化層後使用了LRN層(區域性相應歸一化層),增強了模型的泛化能力。
建立2個卷積層,3個全連線層:
建立第一個卷積層,首先通過損失函式建立卷積核的引數並進行初始化,卷積核尺寸為5*5,3個顏色通道,64個卷積核(卷積核深度為64),設定weight初始化標準差為0.05,不對第一層卷積層的weight進行L2正則化處理,即wl設為0。在ReLU啟用函式之後,我們採用一個3*3的步長為2*2的池化核進行最大池化處理(注意這裡最大池化的尺寸和步長不一致),這樣可以增加資料的豐富性。隨後我們使用tf.nn.lrn()函式,即對結果進行LRN處理。LRN層(區域性響應歸一化層)模仿了生物神經系統的“側抑制”機制,對區域性神經元的活動建立競爭機制,使得其中響應比較大的值變得相對更大,並抑制其他反饋較小的神經元,增強了模型的泛化能力。LRN對ReLU這種沒有上限邊界的啟用函式比較試用,不適合於Sigmoid這種有固定邊界並且能抑制過大值的啟用函式。
建立第二個卷積層,和建立第一個卷積層一樣,只不過這裡的權重weight的shape中,通道數為64,bias初始化為0.1,最後的最大池化層和LRN層調換了順序,先進行LRN層處理後進行最大池化處理。
建立第一個全連線層,首先將卷積層的輸出的樣本都reshape為一維向量,獲取每個樣本的長度後作為全連線層的輸入單元數,輸出單元數設為384。權重weight初始化並設定L2正則化係數為0.004,我們希望這一層全連線層不要過擬合。
建立第二個全連線層,和第一個全連線層相似,只不過把隱含單元減少一半為192。
建立第三個全連線層,和第一個全連線層相似,只不過把隱含單元變為10。
整個網路的inference部分已經完成,網路結構如表1所示:
Layer名稱 |
描述 |
|
卷積層 |
conv1 |
實現卷積和修正線性啟用 |
pool1 |
最大池化(max pooling) |
|
norm1 |
區域性響應歸一化 |
|
conv2 |
實現卷積和修正線性啟用 |
|
norm2 |
區域性響應歸一化 |
|
pool2 |
最大池化(max pooling) |
|
全連線層 |
local3 |
基於修正線性啟用的全連線層 |
local4 |
基於修正線性啟用的全連線層 |
|
logits |
進行線性變換以輸出logits |
表 1 網路結構
然後,構建CNN的損失函式;
然後,定義優化器,定義計算Top K準確率的操作。
然後,定義會話並進行迭代訓練。首先通過session的run方法執行images_train,labels_train來獲取每批的訓練資料,再將這個batch的訓練資料傳入train_op和loss的計算,記錄每一個step花費的時間。
最後,就是在測試集上測評模型的準確率,這裡是top1準確率,迭代訓練2000次(執行時間30分鐘)後的測評的結果為68.4%。如圖3所示;迭代訓練20000次(執行時間5個小時)後的測評的結果為79.1%。如圖4所示;持續增加迭代次數可以得到更高的準確率。
圖 3 執行結果1
圖 4 執行結果2
Python程式碼:
import time
import math
import numpy as np
import tensorflow as tf
import cifar10,cifar10_input
# cifar10, cifar10_input這兩個程式碼檔案在TensorFlow的官方GitHub上
# 網址https://github.com/tensorflow/models/blob/master/tutorials/image/cifar10
# cifar10:建立CIFAR-10的模型;cifar10_input:讀取本地CIFAR-10的二進位制檔案的內容
max_steps = 2000 # 最大迭代數
batch_size = 128 # 批的大小
data_dir = './cifar-10-batches-bin' # 資料所在路徑
# 判斷cifar10資料集是否存在,若不存在自動下載
cifar10.maybe_download_and_extract()
# 初始化weight函式,通過wl引數控制L2正則化大小
def variable_with_weight_loss(shape, stddev, wl):
var = tf.Variable(tf.truncated_normal(shape, stddev=stddev))
if wl is not None:
# L2正則化可用tf.contrib.layers.l2_regularizer(lambda)(w)實現,自帶正則化引數
weight_loss = tf.multiply(tf.nn.l2_loss(var), wl, name='weight_loss')
tf.add_to_collection('losses', weight_loss)
return var
# 此處的cifar10_input.distorted_inputs()和cifar10_input.inputs()函式
# 都是TensorFlow的操作operation,需要在會話中run來實際執行
# distorted_inputs()函式對資料進行了資料增強
images_train, labels_train = cifar10_input.distorted_inputs(data_dir=data_dir, batch_size=batch_size)
# 裁剪圖片正中間的24*24大小的區塊並進行資料標準化操作
images_test, labels_test = cifar10_input.inputs(eval_data=True,
data_dir=data_dir,
batch_size=batch_size)
# 定義placeholder
# 注意此處輸入尺寸的第一個值應該是batch_size而不是None
image_holder = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])
label_holder = tf.placeholder(tf.int32, [batch_size])
# 定義網路
# 卷積層1,不對權重進行正則化
weight1 = variable_with_weight_loss([5, 5, 3, 64], stddev=5e-2, wl=0.0) # 0.05
kernel1 = tf.nn.conv2d(image_holder, weight1,
strides=[1, 1, 1, 1], padding='SAME')
bias1 = tf.Variable(tf.constant(0.0, shape=[64]))
conv1 = tf.nn.relu(tf.nn.bias_add(kernel1, bias1)) # 實現卷積和修正線性啟用
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1], padding='SAME') # 最大池化(max pooling)
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75) # 區域性響應歸一化
# 卷積層2
weight2 = variable_with_weight_loss([5, 5, 64, 64], stddev=5e-2, wl=0.0)
kernel2 = tf.nn.conv2d(norm1, weight2, strides=[1, 1, 1, 1], padding='SAME')
bias2 = tf.Variable(tf.constant(0.1, shape=[64]))
conv2 = tf.nn.relu(tf.nn.bias_add(kernel2, bias2)) # 實現卷積和修正線性啟用
norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75) # 區域性響應歸一化
pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1], padding='SAME') # 最大池化(max pooling)
# 全連線層3
reshape = tf.reshape(pool2, [batch_size, -1]) # 將每個樣本reshape為一維向量
dim = reshape.get_shape()[1].value # 取每個樣本的長度
weight3 = variable_with_weight_loss([dim, 384], stddev=0.04, wl=0.004)
bias3 = tf.Variable(tf.constant(0.1, shape=[384]))
local3 = tf.nn.relu(tf.matmul(reshape, weight3) + bias3) # 基於修正線性啟用的全連線層
# 全連線層4
weight4 = variable_with_weight_loss([384, 192], stddev=0.04, wl=0.004)
bias4 = tf.Variable(tf.constant(0.1, shape=[192]))
local4 = tf.nn.relu(tf.matmul(local3, weight4) + bias4) # 基於修正線性啟用的全連線層
# 全連線層5
weight5 = variable_with_weight_loss([192, 10], stddev=1 / 192.0, wl=0.0)
bias5 = tf.Variable(tf.constant(0.0, shape=[10]))
logits = tf.matmul(local4, weight5) + bias5 # 模型inference的輸出結果
# 定義損失函式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')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
return tf.add_n(tf.get_collection('losses'), name='total_loss')
loss = loss(logits, label_holder) # 定義loss
train_op = tf.train.AdamOptimizer(1e-3).minimize(loss) # 定義優化器
top_k_op = tf.nn.in_top_k(logits, label_holder, 1)
# 定義會話並開始迭代訓練
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
# 啟動圖片資料增強的執行緒佇列
tf.train.start_queue_runners()
# 迭代訓練
for step in range(max_steps):
start_time = time.time()
image_batch, label_batch = sess.run([images_train, labels_train]) # 獲取訓練資料
_, loss_value = sess.run([train_op, loss],
feed_dict={image_holder: image_batch,
label_holder: label_batch})
duration = time.time() - start_time # 計算每次迭代需要的時間
if step % 10 == 0:
examples_per_sec = batch_size / duration # 每秒處理的樣本數
sec_per_batch = float(duration) # 每批需要的時間
format_str = ('step %d, loss=%.2f (%.1f examples/sec; %.3f sec/batch)')
print(format_str % (step, loss_value, examples_per_sec, sec_per_batch))
# 在測試集上測評準確率
num_examples = 10000 # 樣本數量
num_iter = int(math.ceil(num_examples / batch_size))
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_holder: image_batch,
label_holder: label_batch})
true_count += np.sum(predictions)
step += 1
# 輸出正確率
precision = true_count / total_sample_count
print('precision @ 1 =%.3f' % precision)
cifar10.py
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 = 'https://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz'
def _activation_summary(x):
"""Helper to create summaries for activations."""
# 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."""
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."""
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. """
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."""
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."""
# 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=None)
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=None)
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, [images.get_shape().as_list()[0], -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=None)
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."""
# 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."""
# 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."""
# 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)
with tf.control_dependencies([apply_gradient_op]):
variables_averages_op = variable_averages.apply(tf.trainable_variables())
return variables_averages_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)
cifar10_input.py
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."""
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."""
# 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."""
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)
with tf.name_scope('data_augmentation'):
# 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."""
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)
with tf.name_scope('input'):
# 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)
注:本文主要參考了 marsjhao的部落格《TensorFlow應用之進階版卷積神經網路CNN在CIFAR-10資料集上分類》地址:https://blog.csdn.net/marsjhao/article/details/72900646