Tensorflow实现Softmax Regression识别手写数字

神经网络的隐含层越多，就可以对原有特征进行越抽象的变化，模型的拟合能力就越强，这就是多层神经网络的功能所在。当我们给Softmax Regression神经网络中加入一个隐含层，正确率会从92%提升到98%。

有隐含层的Softmax Regression只能直接从图像的像素点推断是哪个数字，而没有特征抽象的过程，多层神经网络依靠隐含层，则可以组合出高阶特征，比如横线、竖线、圆圈等，之后可以将这些高阶特征或者说组件在组合成数字，就能实现精准的匹配和分类。即使我们使用很深的网络、很多的隐藏节点、很大的迭代轮数、也很难在MNIST数据集上达到99%以上准确率。之后可以使用 卷积神经网络可以达到约99.2%。

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist=input_data.read_data_sets("MNIST_data/",one_hot=True)
sess=tf.InteractiveSession()

in_units=784
h1_units=300
W1=tf.Variable(tf.truncated_normal([in_units,h1_units],stddev=0.1))
b1=tf.Variable(tf.zeros([h1_units]))
W2=tf.Variable(tf.zeros([h1_units,10]))
b2=tf.Variable(tf.zeros([10]))

x=tf.placeholder(tf.float32,[None,in_units])
keep_prob=tf.placeholder(tf.float32)

hidden1=tf.nn.relu(tf.matmul(x,W1)+b1)
hidden1_drop=tf.nn.dropout(hidden1,keep_prob)
y=tf.nn.softmax(tf.matmul(hidden1_drop,W2)+b2)

y_=tf.placeholder(tf.float32,[None,10])
cross_entropy=tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y),
                                            reduction_indices=[1]))
train_step=tf.train.AdagradOptimizer(0.3).minimize(cross_entropy)

tf.global_variables_initializer().run()
for i in range(3000):
    batch_xs,batch_ys=mnist.train.next_batch(100)
    train_step.run({x:batch_xs,y_:batch_ys,keep_prob:0.75})

correct_prediction=tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
print(accuracy.eval({x:mnist.test.images,y_:mnist.test.labels,
                     keep_prob:1.0}))

0.9793

利用卷积网络实现：

"""Tensorflow实现简单的卷积网络"""
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist=input_data.read_data_sets("MNIST_data/",one_hot=True)
sess=tf.InteractiveSession()

def weight_variable(shape):
    initial=tf.truncated_normal(shape,stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial=tf.constant(0.1,shape=shape)
    return tf.Variable(initial)

def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')

def max_pool_2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],
                          padding='SAME')
    
x=tf.placeholder(tf.float32,[None,784])
y_=tf.placeholder(tf.float32,[None,10])
x_image=tf.reshape(x,[-1,28,28,1])

W_conv1=weight_variable([5,5,1,32])
b_conv1=bias_variable([32])
h_conv1=tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
h_pool1=max_pool_2x2(h_conv1)

W_conv2=weight_variable([5,5,32,64])
b_conv2=bias_variable([64])
h_conv2=tf.nn.relu(conv2d(h_pool1,W_conv2)+b_conv2)
h_pool2=max_pool_2x2(h_conv2)

W_fc1=weight_variable([7*7*64,1024])
b_fc1=bias_variable([1024])
h_pool2_flat=tf.reshape(h_pool2,[-1,7*7*64])
h_fc1=tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)

keep_prob=tf.placeholder(tf.float32)
h_fc1_drop=tf.nn.dropout(h_fc1,keep_prob)

W_fc2=weight_variable([1024,10])
b_fc2=bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)

cross_entropy=tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y_conv),
                                            reduction_indices=[1]))
train_step=tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction=tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

tf.global_variables_initializer().run()
for i in range(20000):
    batch=mnist.train.next_batch(50)
    if i%100==0:
        train_accuracy=accuracy.eval(feed_dict={x:batch[0],y_:batch[1],
                                                keep_prob:1.0})
        print("step %d,training accuracy %g"%(i,train_accuracy))
    train_step.run(feed_dict={x:batch[0],y_:batch[1],keep_prob:0.5})
    
print("test accuracy %g"%accuracy.eval(feed_dict={
        x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))

 

step 0,training accuracy 0.04
step 1000,training accuracy 0.96
step 2000,training accuracy 0.98
step 3000,training accuracy 1
step 4000,training accuracy 0.98
step 5000,training accuracy 1
step 6000,training accuracy 1
step 7000,training accuracy 0.96
step 8000,training accuracy 0.96
step 9000,training accuracy 1
step 10000,training accuracy 1
step 11000,training accuracy 1
step 12000,training accuracy 1
step 13000,training accuracy 1
step 14000,training accuracy 1
step 15000,training accuracy 1
step 16000,training accuracy 1
step 17000,training accuracy 1
step 18000,training accuracy 1
step 19000,training accuracy 1
test accuracy 0.9918

 

cpu跑得太慢了， 早知道安装GPU了！ ！！ ！！ ！