(一)Tensorflow創建一個簡單的CNN模型

參考:https://www.jianshu.com/p/e2f62043d02b

利用tensorflow框架和Python語言編寫一個簡單的卷積神經網絡結構CNN來識別手寫數字(mnist數據集方便調用)

網絡一共包括4層,分別是

  • 卷積層conv1+池化pooling
  • 卷積層conv2+池化pooling
  • 全連接層fc1+dropout
  • 全連接層fc1+softmax(預測)
import tensorflow as tf
# 導入tensorflow自帶的mnist數據集
from tensorflow.examples.tutorials.mnist import input_data
# 讀入
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

# 產生隨機變量,符合 normal 分佈
# 傳遞 shape 就可以返回weight和bias的變量
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)

# 定義2維的 convolutional 圖層
def conv2d(x, W):
    # stride [1, x_movement, y_movement, 1]
    # Must have strides[0] = strides[3] = 1
    # strides 就是跨多大步抽取信息
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')     

# 定義 pooling 圖層
def max_pool_2x2(x):
    # stride [1, x_movement, y_movement, 1]
    # 用pooling對付跨步大丟失信息問題
    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])        # 784=28x28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])           # 最後一個1表示數據是黑白的,彩色是3
# print(x_image.shape)  # [n_samples, 28,28,1]

## 1.第1個卷積層
#  把x_image的厚度1加厚變成了32
W_conv1 = weight_variable([5, 5, 1, 32])            # patch 5x5, in size 1, out size 32
b_conv1 = bias_variable([32])
# 構建第一個convolutional層,外面再加一個非線性化的處理relu
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)       # output size 28x28x32
# 經過pooling後,長寬縮小爲14x14
h_pool1 = max_pool_2x2(h_conv1)                                # output size 14x14x32

## 2. 第2個卷積層
# 把厚度32加厚變成了64
W_conv2 = weight_variable([5,5, 32, 64])            # patch 5x5, in size 32, out size 64
b_conv2 = bias_variable([64])
# 構建第二個convolutional層
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)       # output size 14x14x64
# 經過pooling後,長寬縮小爲7x7
h_pool2 = max_pool_2x2(h_conv2)                                # output size 7x7x64

## 3. 第1個全連接層
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
# [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
# 把pooling後的結果變平
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)

## 4. 第2個全連接層
# 最後一層,輸入1024,輸出size 10,用 softmax 計算概率進行分類的處理
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)


# 計算損失函數
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))      
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(100)   #batch_size
    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))

 

發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章