Tensorflow学习精要版III---使用cifar10构建更加复杂的模型
总览
主要是
1. 可视化
2. 计算学到的参数的Moving Average
3. 随时间改变的learning_rate
4. 数据预存取队列，将图像预处理操作与模型分开
代码地址：tensorflow/models/image/cifar10/
主要分为三个部分：
模型输入
inputs()和distorted_inputs()用于读取图片以及扭曲图片。因为每张图片存储字节数是固定的，所以可以用tf.FixedLengthRecordReader函数。
显然一般输入的图片要裁剪掉边缘，这里是24*24大小。然后whiten处理。还有一点就是对数据集一般要进行一些改变，以便训练出的模型对于图片的简单变换具有不变性。简单的扩充数据集就是：旋转，翻转，改亮度，改对比度，或是加入小的噪声之类的。
从磁盘上加载图像并进行变换需要花费不少的处理时间。为了避免这些操作减慢训练过程，我们在16个独立的线程中并行进行这些操作，这16个线程被连续的安排在一个TensorFlow队列中。
#几个重要的函数分析
#该函数主要是进行读取finename_queue队列，只读取一张图片。
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:
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
#存储格式是 label后面跟着image内容
record_bytes = label_bytes + image_bytes
#cifar10的数据没有header和footer，所以直接从0开始读就行。
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
#此时读出的value是很多个固定大小(label+one_image)的内容
result.key, value = reader.read(filename_queue)
#转成uint8格式，
record_bytes = tf.decode_raw(value, tf.uint8)
#第一位就是label。进行裁剪，然而label要求是int32类型，因此再转。
result.label = tf.cast(
tf.slice(record_bytes, [0], [label_bytes]), tf.int32)
#从label_bytes开始，读取image_bytes个位。
depth_major = tf.reshape(tf.slice(record_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.image_summary('images', images)
return images, tf.reshape(label_batch, [batch_size])突然不想写了。。这个还不如看代码呢。没啥好分析的，最多是一些内置函数写一下。。
模型预测
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from datetime import datetime
import os.path
import time
import numpy as np
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
from tensorflow.models.image.cifar10 import cifar10
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string('train_dir', '/tmp/cifar10_train',
"""Directory where to write event logs """
"""and checkpoint.""")
tf.app.flags.DEFINE_integer('max_steps', 1000000,
"""Number of batches to run.""")
tf.app.flags.DEFINE_boolean('log_device_placement', False,
"""Whether to log device placement.""")
def train():
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Get images and labels for CIFAR-10.
images, labels = cifar10.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = cifar10.inference(images)
# Calculate loss.
loss = cifar10.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = cifar10.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.all_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.global_variables_initializer()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement))
sess.run(init)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)
for step in xrange(FLAGS.max_steps):
start_time = time.time()
_, loss_value = sess.run([train_op, loss])
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 10 == 0:
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print (format_str % (datetime.now(), step, loss_value,
examples_per_sec, sec_per_batch))
if step % 100 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
# Save the model checkpoint periodically.
if step % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
def main(argv=None): # pylint: disable=unused-argument
cifar10.maybe_download_and_extract()
if tf.gfile.Exists(FLAGS.train_dir):
tf.gfile.DeleteRecursively(FLAGS.train_dir)
tf.gfile.MakeDirs(FLAGS.train_dir)
train()
if __name__ == '__main__':
tf.app.run()