tensorflow minist数据集分类笔记
本文作为笔者对于tensorflow源码学习的一个笔记，将详细阐述minist教程中cnn网络的实现及其代码细节：
# 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 simple MNIST classifier which displays summaries in TensorBoard.
This is an unimpressive MNIST model, but it is a good example of using
tf.name_scope to make a graph legible in the TensorBoard graph explorer, and of
naming summary tags so that they are grouped meaningfully in TensorBoard.
It demonstrates the functionality of every TensorBoard dashboard.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
头文件声明，其中input_data为tutorial中自己撰写的用于读取minist数据集的模块
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_boolean('fake_data', False, 'If true, uses fake data '
'for unit testing.')
flags.DEFINE_integer('max_steps', 1000, 'Number of steps to run trainer.')
flags.DEFINE_float('learning_rate', 0.001, 'Initial learning rate.')
flags.DEFINE_float('dropout', 0.9, 'Keep probability for training dropout.')
flags.DEFINE_string('data_dir', '/tmp/data', 'Directory for storing data')
flags.DEFINE_string('summaries_dir', '/tmp/mnist_logs', 'Summaries directory')
类似g-flags的实现，定义函数参量及其默认值。虽然用法和g-flags极其相似但是据：http://stackoverflow.com/questions/33932901/whats-the-purpose-of-tf-app-flags-in-tensorflow说这里并非g-flags库实现而是一个极其相似的实现。另外 ，该部分并非tensorflow的公开API，只是作为小工具使用，所以在未来的版本很可能更换或者修改。
def train():
# Import data
mnist = input_data.read_data_sets(FLAGS.data_dir,
one_hot=True,
fake_data=FLAGS.fake_data)
读取mnist数据集。
sess = tf.InteractiveSession()
定义会话情景。在tensorflow的程序中，这是必要的。
# Create a multilayer model.
# Input placehoolders
with tf.name_scope('input'):
该函数为tf.Graph.name_scope(name)的封装，输入一个不以“\”结尾的字符串，输出一个在图中属于下一级结构的操作体（operation）。
x = tf.placeholder(tf.float32, [None, 784], name='x-input')
y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')
创建一个存放临时变量的张量结构。该结构不需要初始化，需要有feed_back方法为其获取数据。
在这里我们做一下tensorflow里面常用的variable，constant以及placeholder的对比：
- variable :最常用的结构，必须被初始化，可以被存储到硬盘中并读取。
- constants：常量张量结构，其包含内容不会改变。需要在声明时刻就指明其内容。其还包含一些变体：
- Sequences：包含linspace，与numpylinspace相同；range，与python中的range相同
- Random Tensors：按照规定分布生成随机数，需要在session中进行初始化（调用run）
- placeholders:存放临时变量的结构，不需要初始化，但是需要有feedback.使用 feed_dict 在 run() 或者 eval() 执行的时候注入数据。
name参数为其在图中的oeration名。
with tf.name_scope('input_reshape'):
image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
将输入图像集合reshape为28X28单通道图像集合
tf.image_summary('input', image_shaped_input, 10)
和protocolbuffer有关
# We can't initialize these variables to 0 - the network will get stuck.
def weight_variable(shape):
"""Create a weight variable with appropriate initialization."""
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
生成截尾正太分布数据
def bias_variable(shape):
"""Create a bias variable with appropriate initialization."""
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
生成值全为0.1的数组作为偏置
def variable_summaries(var, name):
"""Attach a lot of summaries to a Tensor."""
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
计算平均值，在没有指定计算坐标轴的情况下，将会计算所有数值的平均值
tf.scalar_summary('mean/' + name, mean)
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_sum(tf.square(var - mean)))
计算标准差
tf.scalar_summary('sttdev/' + name, stddev)
tf.scalar_summary('max/' + name, tf.reduce_max(var))
tf.scalar_summary('min/' + name, tf.reduce_min(var))
tf.histogram_summary(name, var)
def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
"""Reusable code for making a simple neural net layer.
It does a matrix multiply, bias add, and then uses relu to nonlinearize.
It also sets up name scoping so that the resultant graph is easy to read,
and adds a number of summary ops.
"""
# Adding a name scope ensures logical grouping of the layers in the graph.
with tf.name_scope(layer_name):
# This Variable will hold the state of the weights for the layer
with tf.name_scope('weights'):
weights = weight_variable([input_dim, output_dim])
variable_summaries(weights, layer_name + '/weights')
在此处生成权重
with tf.name_scope('biases'):
biases = bias_variable([output_dim])
variable_summaries(biases, layer_name + '/biases')
生成偏置
with tf.name_scope('Wx_plus_b'):
preactivate = tf.matmul(input_tensor, weights) + biases
tf.histogram_summary(layer_name + '/pre_activations', preactivate)
activations = act(preactivate, 'activation')
tf.histogram_summary(layer_name + '/activations', activations)
return activations
生成该层并确定激活函数
hidden1 = nn_layer(x, 784, 500, 'layer1')
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
tf.scalar_summary('dropout_keep_probability', keep_prob)
dropped = tf.nn.dropout(hidden1, keep_prob)
防止过拟合的dropout网络模型
y = nn_layer(dropped, 500, 10, 'layer2', act=tf.nn.softmax)
with tf.name_scope('cross_entropy'):
diff = y_ * tf.log(y)
with tf.name_scope('total'):
cross_entropy = -tf.reduce_mean(diff)
tf.scalar_summary('cross entropy', cross_entropy)
交叉熵误差
with tf.name_scope('train'):
train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(
cross_entropy)
优化方法
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.scalar_summary('accuracy', accuracy)
验证数据集合是否正确
# Merge all the summaries and write them out to /tmp/mnist_logs (by default)
merged = tf.merge_all_summaries()
这样来说的话，之前的工作就相当一直在描述整个图？
train_writer = tf.train.SummaryWriter(FLAGS.summaries_dir + '/train',
sess.graph)
test_writer = tf.train.SummaryWriter(FLAGS.summaries_dir + '/test')
tf.initialize_all_variables().run()
# Train the model, and also write summaries.
# Every 10th step, measure test-set accuracy, and write test summaries
# All other steps, run train_step on training data, & add training summaries
def feed_dict(train):
"""Make a TensorFlow feed_dict: maps data onto Tensor placeholders."""
if train or FLAGS.fake_data:
xs, ys = mnist.train.next_batch(100, fake_data=FLAGS.fake_data)
k = FLAGS.dropout
else:
xs, ys = mnist.test.images, mnist.test.labels
k = 1.0
return {x: xs, y_: ys, keep_prob: k}
for i in range(FLAGS.max_steps):
if i % 10 == 0: # Record summaries and test-set accuracy
summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
test_writer.add_summary(summary, i)
print('Accuracy at step %s: %s' % (i, acc))
else: # Record train set summaries, and train
if i % 100 == 99: # Record execution stats
run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
summary, _ = sess.run([merged, train_step],
feed_dict=feed_dict(True),
options=run_options,
run_metadata=run_metadata)
train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
train_writer.add_summary(summary, i)
print('Adding run metadata for', i)
else: # Record a summary
summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))tensorflow
train_writer.add_summary(summary, i)
train_writer.close()
test_writer.close()
def main(_):
if tf.gfile.Exists(FLAGS.summaries_dir):
tf.gfile.DeleteRecursively(FLAGS.summaries_dir)
tf.gfile.MakeDirs(FLAGS.summaries_dir)
train()
if __name__ == '__main__':
tf.app.run()