CNN - 分類器

1. CNN - 分類器

實現對mnist數據集圖片進行識別分類

## 2019.11.1
## 使用mnist數據集， 訓練一個CNN分類器
## mnist: x: [-1, 28, 28, 1] y: [-1, 10]

import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import matplotlib.pyplot as plt

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

def weight_variable(shape):
 ## tf.truncated_normal 產生正態分佈數據， mean-2std , mean+2std
 weight = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(weight)

def bais_variable(shape):
 bais = tf.constant(0.1, shape=shape)
return tf.Variable(bais)


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='VALID')

def compute_accuracy(v_xs, v_ys):
 global predict
 y_pre = sess.run(predict, feed_dict={xs: v_xs})
 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: 0.5})
 print("accuary: {:.3f}".format(result))

xs = tf.placeholder(tf.float32, shape=[None, 28*28]) / 255
ys = tf.placeholder(tf.float32, shape=[None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])

##1 卷積層 池化層
w_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bais_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1) ## 28*28*32
h_pool1 = max_pool_2X2(h_conv1) ## 14*14*32

##2 卷積層 池化層
w_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bais_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2) ## 14*14*64
h_pool2 = max_pool_2X2(h_conv2) ## 7*7*64

## 將數據平滑， 用於全連接
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])

## 全連接
w_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bais_variable([1024])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1)

## dropout keep_prob: 保存的可能性
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

## softmax層
w_fc2 = weight_variable([1024, 10])
b_fc2 = bais_variable([10])
predict = tf.nn.softmax(tf.matmul(h_fc1, w_fc2) + b_fc2)

## 選用交叉熵函數。交叉熵用來衡量預測值和真實值的相似程度，如果完全相同，它們的交叉熵等於零。
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(predict), reduction_indices=1))
train = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

loss = []
with tf.Session() as sess:
 sess.run(tf.global_variables_initializer())
 for i in range(1000):
 batch_xs, batch_ys = mnist.train.next_batch(100)
 sess.run(train, feed_dict={xs:batch_xs, ys:batch_ys, keep_prob:0.5})
 loss.append(sess.run(cross_entropy, feed_dict={xs:batch_xs, ys:batch_ys, keep_prob:0.5}))

 if i % 100 == 0:
 compute_accuracy(mnist.test.images[:1000,:], mnist.test.labels[:1000,:])

plt.plot(list(np.linspace(0, 1000, 1000)), loss, c='red', lw=1)
plt.show()

accuary: 0.071

accuary: 0.851

accuary: 0.903

accuary: 0.925

accuary: 0.946

accuary: 0.955

accuary: 0.959

accuary: 0.963

accuary: 0.965

accuary: 0.971