import pylab
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
tf.reset_default_graph()
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
w = tf.Variable(tf.random_normal([784, 10]))
b = tf.Variable(tf.random_normal([10]))
pred = tf.nn.softmax(tf.matmul(x, w) + b)
# 损失函数
cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), reduction_indices=1))
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
trainging_epochs = 25
batch_size = 100
display_step = 1
saver = tf.train.Saver()
model_path = "models/mnist_model"
def train():
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(trainging_epochs):
avg_cost = 0
total_batch = int(mnist.train.num_examples/batch_size)
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
_, c = sess.run([optimizer, cost], feed_dict={x: batch_xs, y: batch_ys})
avg_cost += c/total_batch
if (epoch + 1) % display_step == 0:
print("epoch:", "%04d" % (epoch + 1), "cost=", "{:.9f}".format(avg_cost))
print("finished")
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print("accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))
saver.save(sess, model_path)
def test():
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, model_path)
# 测试保存的模型正确率
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print("accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))
output = tf.argmax(pred, 1)
batch_xs, batch_ys = mnist.train.next_batch(2)
outputval, predv = sess.run([output, pred], feed_dict={x: batch_xs})
print("outputval:", outputval)
print("predv:", predv)
print("batch_ys:", batch_ys)
im1 = batch_xs[0]
im1 = im1.reshape(-1, 28)
pylab.imshow(im1)
pylab.show()
im2 = batch_xs[1]
im2 = im2.reshape(-1, 28)
pylab.imshow(im2)
pylab.show()
# train()
test()