莫烦Python--Tensorflow Day4

'''CNN卷积神经网络'''
'''整个网络结构就是输入---卷积---池化---卷积---池化---全连接---输出'''
'''
1、convolutional layer1 + max pooling;
2、convolutional layer2 + max pooling;
3、fully connected layer1 + dropout;
4、fully connected layer2 to prediction.
'''
'''
1、一个卷积核对应一层,多个卷积核生成多层
2、一个卷积核(filter/patch/kernal)是:BatchSize * Height * Width * InputDepth * OutputDepth,层数的改变是通过OutputDepth来改变的
3、卷积过程需要用到卷积核,可以理解为一个二维的滑动窗口,每个卷积核由n * m个小格组成,每个小格都有自己的权重值,卷积过程就是将
   卷积核覆盖的像素值乘以对应格子内的系数求和得到一个新的值,由于将n * m个点压缩成一个点,所以长宽会变小,每个卷积核扫描完后产
   生一层图像,多个卷积核就产生多层,高度就会增加(也可以理解为不同卷积核/滤波器处理同一张图片后产生的多张图)。
4、stride步长,跨度为多少 
           -"VALID":输入大小不一样就舍去,输出比原图小,让卷积核使用保守原则,超过卷积核框架的边缘就丢弃
5、padding-|
           -"SAME":输入大小不一样的时候要补0,输出和原图一样大
6、Pooling:相当于一个固化的卷积核,作用不是降维,而是缩小数据点,为了得到主要信息,忽略次要信息,
            池化后长宽不变,高度(filter的个数)不变,max pooling 强调特征,
   average pooling 强调背景
   Alphago用的是补0
7、实际上是卷积窗口大小对应feature map,含义:[batch, height, weight, channels],因为在卷积池化过程中不需要对batch核channels操作,
   所以第一个和最后一个是1
'''

'''CNN 代码'''
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# number 1 to 10
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

# 定义精确度
def compute_accuracy(v_xs, v_ys):
    global prediction
    y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
    correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
    return result

def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)        # 正态分布函数,大部分权重的初始化值都是采用正态分布
    return tf.Variable(initial)

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

def conv2d(x, W):
    # strides[1, x_movement, y_movement, 1]
    # 常见的是[1,2,2,1]或[1,3,3,1],分别表示[batchsize,高,宽,通道数]
    # Must have strides[0] = strides[3] = 1
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
    # ksize就是卷积核的大小,池化窗口大小
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784])/255.       # 28 * 28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
# 第一个参数的意思是batch,意思是由多少个图片,这里含义是有n个28*28,通道为1的图片(channel=1表示灰度,channel=3表示RGB),n根据自己传入的参数自己匹配
# -1表示不知道填什么数据,但是可以通过后面的数据计算出右面的形状,确定以后系统会自动进行一个出发运算,得到图片数,28*28*1是一张图片的像素点数
x_image = tf.reshape(xs, [-1, 28, 28, 1])           # -1代表不指定这一维的大小,函数自己判断
#print(x_image.shape)                                # [n_samples,28,28,1]

# conv1 layer ##
W_conv1 = weight_variable([5, 5, 1, 32])                    # patch: 5*5,  in_size 1(输入通道数,灰度图像), out size 32(输出通道数,滤波器数,自己设置的)
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)    # output size 28*28*32
h_pool1 = max_pool_2x2(h_conv1)                             # output size 14*14*32  因为步长是2,所以输出缩小了一倍

# conv2 layer ##
W_conv2 = weight_variable([5, 5, 32, 64])                   # patch: 5*5,  in_size 32(输入通道数,灰度图像), out size 64(输出通道数,滤波器数,自己设置的)
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)    # output size 14*14*64
h_pool2 = max_pool_2x2(h_conv2)                             # output size 7*7*64  因为步长是2,所以输出缩小了一倍

# func1 layer ##
W_fc1 = weight_variable([7*7*64, 1024])                     # 1024是人为设置的隐藏层维度,也是第一层全连接层维度
b_fc1 = bias_variable([1024])
# [n_samples,7,7,64] ->> [n_samples,7*7*64]
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)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# func2 layer ##
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

# the error between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),
                                              reduction_indices=[1]))       # loss
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

sess = tf.Session()

# important step
sess.run(tf.initialize_all_variables())

for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(10)
    sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
    if i % 50 == 0:
        print(compute_accuracy(
            mnist.test.images, mnist.test.labels))
        
'''
运行结果:
0.105
0.5958
0.7556
0.8036
0.8297
0.8698
0.8807
0.8979
0.9058
0.9017
0.9179
0.9251
0.9261
0.9259
0.9272
0.9387
0.9382
0.9351
0.94
0.9434

'''
posted @ 2019-12-22 18:23  旅人_Eric  阅读(139)  评论(0编辑  收藏  举报