深度学习之mnist识别-CNN

使用tensorflow框架和python，学习实现简单的CNN网络，并进行调参，代码如下：

#! /usr/bin/python
# -*- coding:utf-8 -*-

import tensorflow as tf
from tinyenv.flags import flags
from tensorflow.examples.tutorials.mnist import input_data
FLAGS = None


def train():
	#读取数据
	mnist = input_data.read_data_sets(FLAGS.data_dir,
									  one_hot = True,
									  fake_data = FLAGS.fake_data)
									  
	sess = tf.InteractiveSession()#可在运行图时插入计算图
	
	with tf.name_scope('input'):#命名空间函数,输入
	    x = tf.placeholder(tf.float32,[None,784],name = 'x-input')
	    y_ = tf.placeholder(tf.float32,[None,10],name = 'y-input')
	  
	with tf.name_scope('input_reshape'):#reshape
		image_shaped_input = tf.reshape(x,[-1,28,28,1])
		tf.summary.image('input',image_shaped_input,10)#记录 可视化
	  
    def weight_variable(shape):
        #权重变量，并初始化
        initial = tf.truncated_normal(shape, stddev=0.1)
        return tf.Variable(initial)
		
	def bias_variable(shape):
        #偏置变量，并初始化
        initial = tf.constant(0.1, shape=shape)
        return tf.Variable(initial)	
	
	def variable_summaries(var):#可视化记录
        with tf.name_scope('summaries'):
            mean = tf.reduce_mean(var)
            tf.summary.scalar('mean', mean)#scalar显示标量信息
            with tf.name_scope('stddev'):
                stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
            tf.summary.scalar('stddev', stddev)
            tf.summary.scalar('max', tf.reduce_max(var))
            tf.summary.scalar('min', tf.reduce_min(var))
            tf.summary.histogram('histogram', var)	#显示训练过程中变量的分布情况
			
	def nn_layer(input_tensor,input_dim,output_dim,layer_name,act = tf.nn.relu):
	#layer_name设置
		with tf.name_scope(layer_name):#权重变量，并记录
			with tf.name_scope('weight'):
				weights = weight_variable([input_dim,output_dim])
				variable_summaries(weights)
			with tf.name_scope('biases'):#偏置
				biases = weight_variable([output_dim])
				variable_summaries(biases) 
			with tf.name_scope('wx+b'):#xw+b
				preactivate = tf.matmul(input_tensor,weights) + biases
				tf.summary.histogram('pre_activations', preactivate)
            activations = act(preactivate, name='activation')#relu激活
            tf.summary.histogram('activations', activations)
            return activations
			
	hidden1 = nn_layer(x,784,500,'layer1')#隐层
	
	with tf.name_scope('dropout'):#定义dropout
		keep_prob = tf.placeholder(tf.float32)
		droped = tf.nn.dropout(hidden1,keep_prob)
		
	y = nn_layer(droped,500,10,'layer2',act = tf.identity)#输出层
	
	 with tf.name_scope('cross_entropy'):#交叉熵
        diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y)
        with tf.name_scope('total'):
            cross_entropy = tf.reduce_mean(diff)
    tf.summary.scalar('cross_entropy', cross_entropy)

    with tf.name_scope('train'):#train
        train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(
            cross_entropy)

    with tf.name_scope('accuracy'):#正确率
        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.summary.scalar('accuracy', accuracy)
	
	merged = tf.summary.merge_all()
    train_writer = tf.summary.FileWriter(FLAGS.log_dir + '/train', sess.graph)
    test_writer = tf.summary.FileWriter(FLAGS.log_dir + '/test')
    tf.global_variables_initializer().run()

    def feed_dict(train):#feed_dict
        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.iterations):
        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:
            if i % 100 == 99:
                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)
            else:
                summary, _ = sess.run(
                    [merged, train_step], feed_dict=feed_dict(True))
                train_writer.add_summary(summary, i)
    train_writer.close()
    test_writer.close()
	
def main(_):
    if tf.gfile.Exists(FLAGS.log_dir):
        tf.gfile.DeleteRecursively(FLAGS.log_dir)
    tf.gfile.MakeDirs(FLAGS.log_dir)
    train()


if __name__ == '__main__':
    FLAGS = flags()
    tf.app.run(main=main, argv=[sys.argv[0]])