[笔记][tf]|[CNN]|[例子3]tensorflow学习笔记（5）

[tf]|[CNN]|[例子3]tensorflow学习笔记（5）

参考：莫烦Python: morvanzhou.github.io

往期链接

[笔记]|[tf]|[张量]|[例子1]tensorflow学习笔记（1）
[笔记][tf]|[例子2]tensorflow学习笔记（2）
[笔记]|[tf]|[tensorboard]|[例子2可视化]tensorflow学习笔记（3）
[笔记]|[tf]|[mnist]tensorflow学习笔记（4）
[笔记]|[tf]|[Saver]|[模型的保存与提取]tensorflow学习笔记（6）

tf(reshape)(xs,[-1,28,28,1])

• • -1为将数据扁平化
  • -1为先不去定义维度的大小，reshape自动计算，但是列表中只能存在一个-1（多个-1会产生多解问题）
• 1为黑白

W_conv1 = weight_variable([5,5,1,32])

• patch：5x5 :（输入5*5的像素）

• in size：1 image的厚度（本层输入通道数，只有灰度所以填1）

• out szie：32 有32不同的feature map用来提取32种特征，不同特征可以用来识别不同类型的图片（卷积核数）（一般设为2的次方值）

• [5,5,1]为卷积核尺寸；32为卷积核数；一层卷积核生成一层feature map

完整代码

"""
Please note, this code is only for python 3+. If you are using python 2+, please modify the code accordingly.
"""
from __future__ import print_function
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# number 1 to 10 data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

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
#输出的结果
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    #产生随机变量     标准差stddev
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    #initial初始化并赋值为0.1
    return tf.Variable(initial)

def conv2d(x, W):
    # stride [1, x_movement, y_movement, 1]
    # Must have strides[0] = strides[3] = 1
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
#x：图片的所有信息； W:卷积核 strides：步长：[batch,height,width,channels]即：图片x,y步长为1  ；
def max_pool_2x2(x):
    # stride [1, x_movement, y_movement, 1]
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
#卷积大小为2*2  步长为2
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784])/255.   # 28x28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])
#传入图片信息
#print(x_image.shape)  # [n_samples, 28,28,1]

## conv1 layer ##
W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32
#patch：见上文图（输入5*5的像素）
#in size：输入为1层，通道数为1（只有灰度）
#out size：卷积核个数（一般取2的次方数）
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32
#与之前例子一样，只是用了conv2d来替换乘法规则
h_pool1 = max_pool_2x2(h_conv1)                          # output size 14x14x32

## conv2 layer ##
W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64
h_pool2 = max_pool_2x2(h_conv2)                          # output size 7x7x64

## fc1 layer ##
#全连接层   与我们之前定义的例子定义的网络一样
W_fc1 = weight_variable([7*7*64, 1024])
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)

## fc2 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
# tf.initialize_all_variables() no long valid from
# 2017-03-02 if using tensorflow >= 0.12
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
    init = tf.initialize_all_variables()
else:
    init = tf.global_variables_initializer()
sess.run(init)

for i in range(10000):
    #迭代3000次准确率能达到0.99
    batch_xs, batch_ys = mnist.train.next_batch(100)
    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[:1000], mnist.test.labels[:1000]))