Tensorflow 基于minst手写数字数据集合建立CNN分类模型

读取数据

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
import input_data
import warnings
warnings.filterwarnings('ignore')
mnist = input_data.read_data_sets('data/', one_hot=True)
trainimg   = mnist.train.images
trainlabel = mnist.train.labels
testimg    = mnist.test.images
testlabel  = mnist.test.labels
print ("MNIST ready")

初始化权重

n_input  = 784
n_output = 10#10分类  图片为28*28*1
weights  = {
        'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=0.1)),#第一层卷积层，1是连接的输入深度，64是特征图
        'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=0.1)),#第一层卷积层，64是连接的输入深度，128是特征图
        'wd1': tf.Variable(tf.random_normal([7*7*128, 1024], stddev=0.1)),#第一层卷积层，28*28通过两次池化变为14*14，7*7，1024定义向量维度
        'wd2': tf.Variable(tf.random_normal([1024, n_output], stddev=0.1))#第二层全连接层
    }
biases   = {
        'bc1': tf.Variable(tf.random_normal([64], stddev=0.1)),#第一层卷积层
        'bc2': tf.Variable(tf.random_normal([128], stddev=0.1)),#第一层卷积层
        'bd1': tf.Variable(tf.random_normal([1024], stddev=0.1)),#第一层卷积层
        'bd2': tf.Variable(tf.random_normal([n_output], stddev=0.1))#第二层全连接层
    }

建立卷积，池化模型

#卷积
def conv_basic(_input, _w, _b, _keepratio):
        # -1为tensor推断第一维的值，h,w都为28，1为通道数（灰度图）
        _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])
        # 第一层卷积层  _w['wc1']为第一层卷积层的参数 SAME pading在无数据时自动填充0
        _conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME')
  
        #创建一个relu函数对卷积层进行非线性变换
        _conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1']))
        #池化  
        #例如mnist中的输入图像为 28 * 28 的黑白图像,其张量即为[batch,28,28,1],
        #1代表黑白,RGB彩色图像的通道则为3,而batch 则为输入的图像数量,一次输入10张图片时,其为10,20张时则为20
        _pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
        #dropout层  _keepratio保留比例
        _pool_dr1 = tf.nn.dropout(_pool1, _keepratio)
        
        # 第二层卷积层 池化 
        _conv2 = tf.nn.conv2d(_pool_dr1, _w['wc2'], strides=[1, 1, 1, 1], padding='SAME')
        _conv2 = tf.nn.relu(tf.nn.bias_add(_conv2, _b['bc2']))
        _pool2 = tf.nn.max_pool(_conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
        _pool_dr2 = tf.nn.dropout(_pool2, _keepratio)
        
        
        # 全连接层1  第一个参数是第二层池化层，第二个参数为全连接层的权重数目
        _dense1 = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]])
        # 全连接层1 激活  _dense1*w1+b
        _fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _w['wd1']), _b['bd1']))
        _fc_dr1 = tf.nn.dropout(_fc1, _keepratio)
        
        # 全连接层2
        _out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2'])
        # RETURN
        out = { 'input_r': _input_r, 'conv1': _conv1, 'pool1': _pool1, 'pool1_dr1': _pool_dr1,
            'conv2': _conv2, 'pool2': _pool2, 'pool_dr2': _pool_dr2, 'dense1': _dense1,
            'fc1': _fc1, 'fc_dr1': _fc_dr1, 'out': _out
        }
        return out
print ("CNN READY")

建立cnn模型（反向传播）

x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
keepratio = tf.placeholder(tf.float32)

# 模型
#预测值
_pred = conv_basic(x, weights, biases, keepratio)['out']
#loss
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=_pred, labels=y))
#使用自适应矩估计梯度下降
optm = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
#计算准确率
_corr = tf.equal(tf.argmax(_pred,1), tf.argmax(y,1)) 
accr = tf.reduce_mean(tf.cast(_corr, tf.float32)) 
#初始化session
init = tf.global_variables_initializer()
    
# SAVER
print ("GRAPH READY")

迭代，模型求解

sess = tf.Session()
sess.run(init)

training_epochs = 15
batch_size      = 16
display_step    = 1
for epoch in range(training_epochs):
    avg_cost = 0.
    #total_batch = int(mnist.train.num_examples/batch_size)
    total_batch = 10
    # Loop over all batches
    for i in range(total_batch):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        # Fit training using batch data
        sess.run(optm, feed_dict={x: batch_xs, y: batch_ys, keepratio:0.7})
        # Compute average loss
        avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})/total_batch

    # Display logs per epoch step
    if epoch % display_step == 0: 
        print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
        train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})
        print (" Training accuracy: %.3f" % (train_acc))
        #test_acc = sess.run(accr, feed_dict={x: testimg, y: testlabel, keepratio:1.})
        #print (" Test accuracy: %.3f" % (test_acc))

print ("OPTIMIZATION FINISHED")

可以发现，卷积神经网络比之逻辑回归准确率更高，比之BP神经网络更容易收敛

Tensorflow 基于minst手写数字数据集合建立CNN分类模型

猜你喜欢