在之前的博客中已经对CIFAR-10做了整体的解析,但是目前从tensorflow/models/tree/master/tutorials/image/cifar10中下载下来,运行cifar10_train.py后训练的是binary(适用于C语言)版的数据集。
其实主要需要修改的部分是cifar10_input.py文件。因为python版本的数据集形式不相同,具体格式请上Alex官网的The CIFAR-10 dataset去了解。因为格式不同,导入数据集的代码部分对于数据集的解析也就不相同。python版如下:
def unpickle(file):
import pickle
with open(file, 'rb') as fo:
dict = pickle.load(fo, encoding='bytes')
return dict
这里就不罗嗦啦,直接向大家奉上整个代码:
from __future__ import print_function
import os
import tensorflow as tf
import pickle as pickle
import numpy as np
from PIL import Image
#encoding:utf-8
from scipy import ndimage
# Global constants describing the CIFAR-10 data set
# CIFAR10 image size of 32x32. will distort to 24x24
IMAGE_SIZE = 24
NUM_CLASSES = 10
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 50000
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = 10000
# train_data_queue = None
# train_labels_queue = None
# train_f_names_queue = None
#读取数据集中的各个文件,按照类型生成相应格式,或列表 或矩阵
def read_cifar10_python_pickles(filenames):
data = None
labels = None
f_names = None
# Dict Keys from pickle files
# ['data', 'labels', 'batch_label', 'filenames']
"""
filenames = [os.path.join(data_dir, 'data_batch_%d' % i)
for i in xrange(1, 6)]"""
for pickle_file in filenames:
if not tf.gfile.Exists(pickle_file):
raise ValueError('Failed to find file: ' + pickle_file)
with open(pickle_file, 'rb') as p:
# pickle.load(file,*,fix_imports=True, encoding="ASCII", errors="strict")
#必填参数file必须以二进制可读模式打开,即“rb”,其他都为可选参数
save = pickle.load(p,encoding='iso-8859-1')
s_data = save['data']
s_labels = np.array(save['labels'])
s_f_names = np.array(save['filenames'])
# 删除列表
del save
print('data set', s_data.shape, s_labels.shape)
#numpy提供了numpy.append(arr, values, axis=None)函数。对于参数规定,
# 要么一个数组和一个数值;要么两个数组,不能三个及以上数组直接append拼接。append函数返回的始终是一个一维数组。
data = np.append(data, s_data, axis=0) if data is not None else s_data
labels = np.append(labels, s_labels, axis=0) if labels is not None else s_labels
f_names = np.append(f_names, s_f_names, axis=0) if f_names is not None else s_f_names
print('Data set: ', data.shape, len(labels))
return data, labels, f_names
def read_cifar10_python_pickle(filename):
if not tf.gfile.Exists(filename):
raise ValueError('Failed to find file: ' + filename)
with open(filename, 'rb') as p:
save = pickle.load(p,encoding='iso-8859-1')
data = save['data']
labels = np.array(save['labels'])
f_names = np.array(save['filenames'])
del save
print('data set', data.shape, labels.shape)
return data, labels, f_names
def read_cifar10_to_queue(filenames):
data, labels, f_names = read_cifar10_python_pickles(filenames)
# def input_producer(input_tensor,
# element_shape=None,
# num_epochs=None,
# shuffle=True,
# seed=None,
# capacity=32,
# shared_name=None,
# summary_name=None,
# name=None,
# cancel_op=None):
#这个地方是将数据按照类型作用进行生成队列
data_queue = tf.train.input_producer(data, shuffle=False)
labels_queue = tf.train.input_producer(labels, shuffle=False)
f_names_queue = tf.train.input_producer(f_names, shuffle=False)
return data_queue, labels_queue, f_names_queue
def read_cifar10_reader(data_q, labels_q):
#dequeue,函数名,用于移除每个匹配元素的指定队列中的第一个函数,并执行被移除的函数。
#将元素从队列中移出。如果在执行该操作时队列已空,
#那么将会阻塞直到元素出列,返回出列的tensors的tuple
return data_q.dequeue(), labels_q.dequeue()
def read_cifar10(filenames):
class CIFAR10Record(object):
pass
result = CIFAR10Record()
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
data_q, label_q, _ = read_cifar10_to_queue(filenames)
data, label = read_cifar10_reader(data_q, label_q)
print(data.get_shape(), data.dtype)
print(label.get_shape(), label.dtype)
result.label = tf.cast(label, tf.int32)#uint8转变成int32数据类型
depth_major = tf.reshape(data, [result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
print(depth_major.get_shape(), depth_major.dtype)
print(result.label.get_shape(), result.label.dtype)
return result
# 构建一个排列后的一组图片和分类
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:
# tf.train.batch(tensors, batch_size, num_threads=1, capacity=32,
# enqueue_many=False, shapes=None, dynamic_pad=False,
# allow_smaller_final_batch=False, shared_name=None, name=None)
# 这里是用队列实现,已经默认使用enqueue_runner将enqueue_runner加入到Graph'senqueue_runner集合中
# 其默认enqueue_many=False时,输入的tensor为一个样本【x,y,z】,输出为Tensor的一批样本
# capacity:队列中允许最大元素个数
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.image_summary('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' % i) for i in range(1,6)]
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
read_input = read_cifar10(filenames)
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)
# Ensure that the random shuffling has good mixing properties.
# min_queue_examples: train(50000*0.4=20000) eval(10000*0.4=4000)
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' % i) for i in range(1, 6)]
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
else:
filenames = [os.path.join(data_dir, 'test_batch')]
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)
read_input = read_cifar10(filenames)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
width, height)
float_image = tf.image.per_image_whitening(resized_image)
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(num_examples_per_epoch * min_fraction_of_examples_in_queue)
return _generate_image_and_label_batch(float_image, read_input.label,
min_queue_examples, batch_size,
shuffle=False)
def test_inputs(data_dir):
filenames = [os.path.join(data_dir, 'test_batch')]
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
read_input = read_cifar10(filenames)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
width, height)
float_image = tf.image.per_image_whitening(resized_image)
return_image = tf.reshape(float_image, [-1, height, width, 3])
return return_image, read_input.label
def test_input_process(image, label=None):
reshaped_image = tf.cast(image, tf.float32)
if label is not None:
label = tf.cast(label, tf.int32)
height = IMAGE_SIZE
width = IMAGE_SIZE
resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
width, height)
float_image = tf.image.per_image_whitening(resized_image)
return_image = tf.reshape(float_image, [-1, height, width, 3])
return return_image, label
def read_n_preprocess_external_input(image_file):
temp_image = Image.open(image_file)
height = temp_image.size[1]
width = temp_image.size[0]
if height > width:
temp_image = temp_image.crop((0, (height - width)/2, width, (height + width)/2))
elif height < width:
temp_image = temp_image.crop(((width - height)/2, 0, (height + width)/2, height))
temp_image.thumbnail((32, 32), Image.ANTIALIAS)
temp_image_arr = np.array(temp_image)
return temp_image_arr
cifar10.py修改后:
# 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_py',
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.# 衰减呈阶梯函数,控制衰减周期(阶梯宽度)
LEARNING_RATE_DECAY_FACTOR = 0.1 # Learning rate decay factor.# 学习率衰减因子
INITIAL_LEARNING_RATE = 0.1 # Initial learning rate.# 初始学习率
# 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-python.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'):#一个 context manager,用于为新的op指定要使用的硬件
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-py')
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-py')
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
#开始建立网络,第一层卷积层的 weight 不进行 L2正则,因此 kernel(wd) 这一项设为0,建立值为0的 biases,
# conv1的结果由 ReLu 激活,由 _activation_summary() 进行汇总;然后建立第一层池化层,
# 最大池化尺寸和步长不一致可以增加数据的丰富性;最后建立 LRN 层
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 局部相响应归一化
# LRN层模仿了生物神经系统的
# "侧抑制"
# 机制,对局部神经元的活动创建竞争环境,使得其中响应比较大的值变得相对更大,并抑制其他反馈较小的神经元,增强了模型的泛化能力,LRN
# 对Relu 这种没有上限边界的激活函数会比较有用,因为它会从附近的多个卷积核的响应中挑选比较大的反馈,但不适合
# sigmoid这种有固定边界并且能抑制过大的激活函数。
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm1')
# conv2
#第二层卷积层与第一层,除了输入参数的改变之外,将 biases 值全部初始化为0.1,
# 调换最大池化和 LRN 层的顺序,先进行LRN,再使用最大池化层。
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
#第三层全连接层 ,需要先把前面的卷积层的输出结果全部 flatten,
# 使用 tf.reshape 函数将每个样本都变为一维向量,使用 get_shape 函数获取数据扁平化之后的长度;
# 然后对全连接层的 weights 和 biases 进行初始化,为了防止全连接层过拟合,设置一个非零的 wd 值0.004,
# 让这一层的所有参数都被 L2正则所约束,最后依然使用 Relu 激活函数进行非线性化。
# 同理,可以建立第四层全连接层。
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.
#最后的 softmax_linear 层,先创建这一层的 weights 和 biases,不添加L2正则化。
# 在这个模型中,不像之前的例子使用 sotfmax 输出最后的结果,因为将 softmax 的操作放在来计算 loss 的部分,
# 将 softmax_linear 的线性返回值 logits 与 labels 计算 loss,
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
#损失函数
#通过 tf.nn.softmax 后的 logits 值(属于每个类别的概率值)
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)
#在 CIFAR-10 中,labels 的 shape 为 [batch_size],每个样本的 label 为0到9的一个数,代表10个分类,
# 这些类之间是相互排斥的,每个 CIFAR-10 图片只能被标记为唯一的一个标签:一张图片可能是一只狗或一辆卡车,而不能两者都是。
# 因此我们需要对 label 值 onehot encoding,转化过程比较繁琐,
# 新版的 TensorFlow API 支持对唯一值 labels 的 sparse_to_dense,只需要一步:
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')
#这里的 labels 的 shape 为 [batch_size, 1]。
# 再使用 tf.add_to_collection 把 cross entropy 的 loss 添加到整体 losses 的 collection 中。
# 最后,使用 tf.add_n 将整体 losses 的 collection中 的全部 loss 求和,得到最终的 loss 并返回,
# 其中包含 cross entropy loss,还有后两个全连接层中的 weight 的 L2 loss
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.
# 创建一个新的指数滑动均值对象
loss_averages = tf.train.ExponentialMovingAverage(0.9, name='avg')
# 从字典集合中返回关键字'losses'对应的所有变量,包括交叉熵损失和正则项损失
losses = tf.get_collection('losses')
# 创建'shadow variables'并添加维护滑动均值的操作
# apply() 方法会添加 trained variables 的 shadow copies,并添加操作来维护变量的滑动均值到 shadow copies。
# 滑动均值是通过指数衰减计算得到的,shadow variable 的初始化值和 trained variables 相同,
# 其更新公式为 shadow_variable = decay * shadow_variable + (1 - decay) * variable。
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.
#首先定义学习率(learning rate),并设置随迭代次数衰减,并进行 summary:
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.
#对 loss 生成滑动均值和汇总,通过使用指数衰减,来维护变量的滑动均值(Moving Average)。
#当训练模型时,维护训练参数的滑动均值是有好处的,在测试过程中使用滑动参数比最终训练的参数值本身,会提高模型的实际性能即准确率。
loss_averages_op = _add_loss_summaries(total_loss) # 损失变量的更新操作
# Compute gradients.
#定义训练方法与目标,tf.control_dependencies 是一个 context manager,控制节点执行顺序,先执行[ ]中的操作,再执行 context 中的操作:
with tf.control_dependencies([loss_averages_op]):
opt = tf.train.GradientDescentOptimizer(lr)#优化器 随机梯度下降法
grads = opt.compute_gradients(total_loss)# 返回计算出的(gradient, variable) pairs
# Apply gradients.
#返回一步梯度更新操作
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.
#最后,动态调整衰减率,返回模型参数变量的滑动更新操作即 train op:
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-py')
if not os.path.exists(extracted_dir_path):
tarfile.open(filepath, 'r:gz').extractall(dest_directory)
cifar10_train.py修改后:
# 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
parser = cifar10.parser
parser.add_argument('--train_dir', type=str, default='/tmp/cifar10_data_py/cifar10_train',
help='Directory where to write event logs and checkpoint.')
parser.add_argument('--max_steps', type=int, default=10000,
help='Number of batches to run.')
parser.add_argument('--log_device_placement', type=bool, default=False,
help='Whether to log device placement.')
parser.add_argument('--log_frequency', type=int, default=10,
help='How often to log results to the console.')
def train():
"""Train CIFAR-10 for a number of steps."""
# 指定当前图为默认graph
with tf.Graph().as_default():
# 设置trainable=False,是因为防止训练过程中对global_step变量也进行滑动更新操作 global_step = tf.Variable(0, trainable=False)
global_step = tf.train.get_or_create_global_step()
# Get images and labels for CIFAR-10.
# Force input pipeline to CPU:0 to avoid operations sometimes ending up on
# GPU and resulting in a slow down.
with tf.device('/cpu:0'):
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__':
FLAGS = parser.parse_args()
tf.app.run()
#tensorboard --logdir=D:/tmp/cifar10_data_py/cifar10_train
注意,路径部分问题以及之前训练后的cifar10_train文件夹已存在导致出错只有将路径改对,并且删除之前的训练生成的文件夹就可以运行啦。
参考文献链接:
http://www.cs.toronto.edu/~kriz/cifar.html
https://github.com/tensorflow/models/tree/master/tutorials/image/cifar10