Tensorflow測試Mnist手寫資料集
阿新 • • 發佈:2019-01-12
測試Minist 資料集
#!/usr/bin/python
import tensorflow as tf
import sys
from tensorflow.examples.tutorials.mnist import input_data
#定義一個函式,用於初始化所有的權值 W
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
#定義一個函式,用於初始化所有的偏置項 b
def bias_variable(shape) :
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
#定義一個函式,用於構建卷積層
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
#定義一個函式,用於構建池化層
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
#下載並載入資料
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
#資料與標籤的佔位
x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32 ])
#構建網路
x_image = tf.reshape(x, [-1, 28, 28, 1]) #轉換輸入資料shape,以便於用於網路中
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) #第一個卷積層
h_pool1 = max_pool_2x2(h_conv1) #第一個池化層
#初始化權重和偏置
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) #第二個卷積層
h_pool2 = max_pool_2x2(h_conv2) #第二個池化層
# Now image size is reduced to 7*7
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64]) #reshape成向量
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) #第一個全連線層
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) #dropout層
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
#softmax迴歸,得到預測概率
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) #softmax層
#求交叉熵得到殘差
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv)) #交叉熵
train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy) #梯度下降法
#train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) #精確度計算
# tf.session()
sess = tf.InteractiveSession()
sess.run(tf.initialize_all_variables())
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
#訓練,迭代1000次
for i in range(10000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x:batch[0], y_: batch[1], keep_prob: 1.0})
print( "step %d, training accuracy %.3f"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print ("Training finished")
print( "test accuracy %.3f" % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))