基于卷积神经网络的Tensorflow实现MNIST识别

基于卷积神经网络的Tensorflow实现MNIST识别

import keras

import tensorflow as tf
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense,Dropout,Activation
from keras.optimizers import RMSprop
import matplotlib.pyplot as plt
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets('MNIST_data',one_hot=True)
print("训练集图像大小：{}".format(mnist.train.images.shape))
print("训练集标签大小：{}".format(mnist.train.labels.shape))
print("验证集图像大小：{}".format(mnist.validation.images.shape))
print("验证集标签大小：{}".format(mnist.validation.labels.shape))
print("测试集图像大小：{}".format(mnist.test.images.shape))
print("测试集标签大小：{}".format(mnist.test.labels.shape))
x_train,y_train=mnist.train.images,mnist.train.labels
x_valid,y_valid=mnist.validation.images,mnist.validation.labels
x_test,y_test=mnist.test.images,mnist.test.labels


img_size=28*28
num_classes=10
learning_rate=1e-4
epochs=10
batch_size=50




#创建模型
x=tf.placeholder(tf.float32,shape=[None,img_size])
x_shaped=tf.reshape(x,[-1,28,28,1])
y=tf.placeholder(tf.float32,shape=[None,num_classes])
# W=tf.Variable(tf.zeros([img_size,num_classes]))
# b=tf.Variable(tf.zeros([num_classes]))
# y=tf.nn.softmax(tf.matmul(x,W)+b)
# y_=tf.placeholder(tf.float32,[None,10])
# valid_feed_dict={x:x_valid,y_:y_valid}
# test_feed_dict={x:x_test,y_:y_test}
def create_conv2d(input_data,num_input_channels,num_filters,filter_shape,pool_shape,name):
    conv_filter_shape=[filter_shape[0],filter_shape[1],num_input_channels,num_filters]
    weights=tf.Variable(tf.truncated_normal(conv_filter_shape,stddev=0.03),name=name+'_W')
    bias=tf.Variable(tf.truncated_normal([num_filters]),name=name+'_b')
    out_layer=tf.nn.conv2d(input_data,weights,(1,1,1,1),padding='SAME')
    out_layer+=bias
    out_layer=tf.nn.relu(out_layer)
    out_layer=tf.nn.max_pool(out_layer,ksize=(1,pool_shape[0],pool_shape[1],1),strides=(1,2,2,1),padding='SAME')
    return out_layer

layer1=create_conv2d(x_shaped,1,32,(5,5),(2,2),name='layer1')
layer2=create_conv2d(layer1,32,64,(5,5),(2,2),name='layer2')
flattened=tf.reshape(layer2,(-1,7*7*64))
wd1=tf.Variable(tf.truncated_normal((7*7*64,1000),stddev=0.03),name='wd1')
bd1=tf.Variable(tf.truncated_normal([1000],stddev=0.01),name='bd1')
dense_layer1=tf.add(tf.matmul(flattened,wd1),bd1)
dense_layer1=tf.nn.relu(dense_layer1)

wd2=tf.Variable(tf.truncated_normal((1000,num_classes),stddev=0.03),
                name='wd2')
bd2=tf.Variable(tf.truncated_normal([num_classes],stddev=0.01),name='bd2')
dense_layer2=tf.add(tf.matmul(dense_layer1,wd2),bd2)
#添加激活函数的softmax输出层
y_=tf.nn.softmax(dense_layer2)
cost=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_,labels=y))
optimizer=tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
correct_prediction=tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
#训练模型
import math
iteration=0
saver=tf.train.Saver()


with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    batch_count=int(math.ceil(mnist.train.labels.shape[0]/128.0))
    for e in range(epochs):
        for batch_i in range(batch_count):
            batch_start=batch_i*batch_size
            batch_x=mnist.train.images[batch_start:batch_start+batch_size]
            batch_y=mnist.train.labels[batch_start:batch_start+batch_size]
            loss,_=sess.run([cost,optimizer],feed_dict={x:batch_x,y:batch_y})
            if batch_i%20==0:
                print("Epoch:{}/{}".format(e+1,epochs),
                      "Iteartion:{}".format(iteration),
                      "Training loss:{}".format(loss))
            iteration +=1
            if iteration % batch_size==0:
                valid_acc=sess.run(accuracy,feed_dict={x:x_valid,y:y_valid})
                print("Epoch:{}/{}".format(e, epochs),
                      "Iteartion:{}".format(iteration),
                      "Training loss:{}".format(valid_acc))
    saver.save(sess,'checkpoints/mnist_cnn_tf.ckpt')
saver=tf.train.Saver()
with tf.Session() as sess:
    saver.restore(sess,tf.train.latest_checkpoint('checkpoints/'))
    test_acc=sess.run(accuracy,feed_dict={x:x_test,y:y_test})
    print("test accuracy:{}".format(test_acc))