import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# mnist数据集的输入
mnist = input_data.read_data_sets('MNIST_data/', one_hot=True)
# 添加一层layer
def add_layer(inputs, in_size, out_size, activation_fuction):
Weights = tf.Variable(tf.random_normal([in_size, out_size]))
biases = tf.Variable(tf.zeros([1,out_size])+0.1)
Wx_plus_b = tf.matmul(inputs, Weights) + biases
if activation_fuction is None:
outputs = Wx_plus_b
else:
outputs = activation_fuction(Wx_plus_b)
return outputs
# 计算最终的准确度
def compute_accuracy(v_xs, v_ys):
global prediction
y_pre = sess.run(prediction, 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})
return result
# define the placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784])
ys = tf.placeholder(tf.float32, [None, 10])
# add output layer
prediction = add_layer(xs, 784, 10, activation_fuction=tf.nn.softmax)
# loss——交叉熵公式(一般用softmax配合cross entropy)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction), reduction_indices=[1]))
# train_step
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
# initialize
sess = tf.Session()
sess.run(tf.initialize_all_variables())
# train
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={xs:batch_xs, ys:batch_ys})
if i%50==0:
print(compute_accuracy(mnist.test.images, mnist.test.labels))
输出
0.1669
0.6481
0.7441
0.7851
0.8093
0.8218
0.8306
0.8403
0.8479
0.8532
0.856
0.8593
0.8621
0.8643
0.867
0.8698
0.8742
0.874
0.8766
0.8768