tensorflow采用卷积神经网络实现MNIST手写体数字识别

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/fengxianghui01/article/details/82252071

内容为自学，经测试完全有效，正确率为0.99

1、模型的建立

import tensorflow as tf

INPUT_NODE = 784
OUTPUT_NODE = 10

IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10


CONV1_DEEP = 32
CONV1_SIZE = 5
CONV2_DEEP = 64
CONV2_SIZE = 5
FC_SIZE = 512

def inference(input_tensor, train, regularizer):
    with tf.variable_scope('layer1-conv1'):
        conv1_weights = tf.get_variable("weights",
                                        [CONV1_SIZE, CONV1_SIZE, NUM_CHANNELS, CONV1_DEEP],
                                        initializer=tf.truncated_normal_initializer(stddev=0.1))
        conv1_biases = tf.get_variable("bias", [CONV1_DEEP], initializer=tf.constant_initializer(0.0))
        
        conv1 = tf.nn.conv2d(input_tensor, conv1_weights, strides=[1,1,1,1], padding='SAME')
        
        relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_biases))
    
    with tf.name_scope('layer2_pool'):
        pool1 = tf.nn.max_pool(relu1, ksize=[1, 2, 2, 1], strides=[1,2,2,1], padding='SAME')
        
    with tf.variable_scope('layer3_conv2'):
        conv2_weights = tf.get_variable("weghts",
                                        [CONV2_SIZE, CONV2_SIZE, CONV1_DEEP, CONV2_DEEP],
                                        initializer=tf.truncated_normal_initializer(stddev=0.1))
        conv2_biases = tf.get_variable("bias", [CONV2_DEEP], initializer=tf.constant_initializer(0.0))
        
        conv2 = tf.nn.conv2d(pool1, conv2_weights, strides=[1,1,1,1], padding='SAME')
        
        relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_biases))
    with tf.name_scope('layer4_pool'):
        pool2 = tf.nn.max_pool(relu2, ksize=[1, 2, 2, 1], strides=[1,2,2,1], padding='SAME')
    pool_shape = pool2.get_shape().as_list()

    nodes = pool_shape[1]*pool_shape[2]*pool_shape[3]
        
    reshaped = tf.reshape(pool2, [pool_shape[0], nodes])
    
    with tf.variable_scope('layer5_fc1'):
        fc1_weights =tf.get_variable("weights",
                                     [nodes, FC_SIZE],
                                     initializer = tf.truncated_normal_initializer(stddev=0.1))
        if regularizer!=None:
            tf.add_to_collection('losses', regularizer(fc1_weights))
        fc1_biases = tf.get_variable("biases",
                                     [FC_SIZE],
                                     initializer=tf.constant_initializer(0.1))
        fc1 = tf.nn.relu(tf.matmul(reshaped, fc1_weights) + fc1_biases)
        
        if train:fc1=tf.nn.dropout(fc1, 0.5)
        
    with tf.variable_scope('layer6_fc2'):
        fc2_weights = tf.get_variable("weights",
                                      [FC_SIZE, NUM_LABELS],
                                      initializer = tf.truncated_normal_initializer(stddev=0.1))
        if regularizer != None:
            tf.add_to_collection('losses', regularizer(fc2_weights))
        fc2_biases = tf.get_variable("bias",
                                     [NUM_LABELS],
                                     initializer=tf.constant_initializer(0.1))
        logit = tf.matmul(fc1, fc2_weights) + fc2_biases
        
    return logit

2、训练模型并保存

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import numpy as np
import os

#加载mnist_inference.py中定义的常量和前向传播的函数
 
#配置神经网络的参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.01
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99

# 保存模型路径
MODEL_SAVE_PATH = "model/"
MODEL_NAME = "model.ckpt"
 
def train(mnist):
    # 定义输出为4维矩阵的placeholder
    x = tf.placeholder(tf.float32, [
            BATCH_SIZE,
            mnist_inference.IMAGE_SIZE,
            mnist_inference.IMAGE_SIZE,
            mnist_inference.NUM_CHANNELS],
        name='x-input')
    y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
    
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    y = mnist_inference.inference(x,False,regularizer)
    global_step = tf.Variable(0, trainable=False)

    # 定义损失函数、学习率、滑动平均操作以及训练过程。
    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variables_averages_op = variable_averages.apply(tf.trainable_variables())
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
    cross_entropy_mean = tf.reduce_mean(cross_entropy)
    loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
    learning_rate = tf.train.exponential_decay(
        LEARNING_RATE_BASE,
        global_step,
        mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY,
        staircase=True)

    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name='train')
        
    # 初始化TensorFlow持久化类。
    saver = tf.train.Saver()
    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        for i in range(TRAINING_STEPS): 
            xs, ys = mnist.train.next_batch(BATCH_SIZE)

            reshaped_xs = np.reshape(xs, (
                BATCH_SIZE,
                mnist_inference.IMAGE_SIZE,
                mnist_inference.IMAGE_SIZE,
                mnist_inference.NUM_CHANNELS))
            _, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: reshaped_xs, y_: ys})

            if i % 1000 == 0:
                print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)
def main(argv=None):
    mnist = input_data.read_data_sets("/path/to/mnist_data", one_hot = True)
    train(mnist)

if __name__ == '__main__':
    main()

3、测试模型正确率

import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np

import mnist_inference
import mnist_train

EVAL_INTERVAL_SECS = 10

def evaluate(mnist):
    with tf.Graph().as_default() as g:
        x = tf.placeholder(tf.float32, [
                mnist_train.BATCH_SIZE,
                mnist_inference.IMAGE_SIZE,
                mnist_inference.IMAGE_SIZE,
                mnist_inference.NUM_CHANNELS],
                name='x-input')
        y_ = tf.placeholder(
                tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y_input')
        xs,ys = mnist.validation.next_batch(mnist_train.BATCH_SIZE)
        #xs, ys = mnist.train.next_batch(mnist_train.BATCH_SIZE)
        
        reshaped_xs = np.reshape(xs, (
                mnist_train.BATCH_SIZE,
                mnist_inference.IMAGE_SIZE,
                mnist_inference.IMAGE_SIZE,
                mnist_inference.NUM_CHANNELS))
        
        validate_feed = {x:reshaped_xs, y_:ys}
        
        y = mnist_inference.inference(x,False, None)
        
        correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        
        variable_averages = tf.train.ExponentialMovingAverage(
                mnist_train.MOVING_AVERAGE_DECAY)
        variables_to_restore = variable_averages.variables_to_restore()
        saver = tf.train.Saver(variables_to_restore)
        
        while True:
            with tf.Session() as sess:
                ckpt = tf.train.get_checkpoint_state(
                        mnist_train.MODEL_SAVE_PATH)
                if ckpt and ckpt.model_checkpoint_path:
                    saver.restore(sess, ckpt.model_checkpoint_path)
                    global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
                    accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
                    print("After %s training steps, validation ""accuracy = %.6f" %(global_step, accuracy_score))
                else:
                    print('No checpoint file found')
                return
            time.sleep(EVAL_INTERVAL_SECS)
            
def main(argv=None):
    mnist = input_data.read_data_sets("data/", one_hot=True)
    evaluate(mnist)
    
if __name__ == '__main__':
    tf.app.run()

正确率为0.99