Created
March 28, 2018 03:37
-
-
Save eremo2002/578d7e415d732d53877f393db852170f to your computer and use it in GitHub Desktop.
Deep Learning
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import tensorflow as tf | |
import time | |
from tensorflow.examples.tutorials.mnist import input_data | |
tf.reset_default_graph() | |
mnist = input_data.read_data_sets("/data/", one_hot=True) | |
X = tf.placeholder(tf.float32, [None, 28, 28, 1]) | |
Y = tf.placeholder(tf.float32, [None, 10]) | |
W1 = tf.Variable(tf.random_normal(shape=[3, 3, 1, 32], stddev=0.01)) | |
L1 = tf.nn.conv2d(X, W1, strides=[1, 1, 1, 1], padding='SAME') | |
L1 = tf.nn.relu(L1) | |
L1 = tf.nn.max_pool(L1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') | |
# max pooling까지 하면 Volume의 크기는 14x14x32 | |
W2 = tf.Variable(tf.random_normal(shape=[3, 3, 32, 64], stddev=0.01)) | |
L2 = tf.nn.conv2d(L1, W2, strides=[1, 1, 1, 1], padding='SAME') | |
L2 = tf.nn.relu(L2) | |
L2 = tf.nn.max_pool(L1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') | |
# max pooling까지 하면 Volume의 크기는 7x7x64 | |
# fully connected하기 위해 reshape | |
L3 = tf.reshape(L2, [-1, 7 * 7 * 64]) | |
# 10개의 class로 분류하기 위해 Output 10 | |
W3 = tf.Variable(tf.random_normal(shape=[7*7*64, 10], stddev=0.01)) | |
b = tf.Variable(tf.random_normal([10])) | |
hyp = tf.matmul(L3, W3) + b | |
# cost함수와 최적화 | |
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits( | |
logits=hyp, labels=Y)) | |
optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost) | |
sess = tf.Session() | |
sess.run(tf.global_variables_initializer()) | |
start = time.time() | |
total_batch = int(mnist.train.num_examples / 100) | |
batch_size = 100 | |
# training | |
for i in range(10): | |
avg_cost = 0 | |
for j in range(total_batch): | |
batch_xs, batch_ys = mnist.train.next_batch(batch_size) | |
batch_xs = batch_xs.reshape(-1, 28, 28, 1) | |
c, _ = sess.run([cost, optimizer], feed_dict={X : batch_xs, Y : batch_ys}) | |
avg_cost += c | |
avg_cost = avg_cost / total_batch | |
print("epoch : ", (i+1), " cost : ", '{:.5f}'.format(avg_cost)) | |
print("트레이닝 완료") | |
prediction = tf.equal(tf.argmax(hyp, 1), tf.argmax(Y, 1)) | |
accuracy = tf.reduce_mean(tf.cast(prediction, tf.float32)) | |
print("Accuracy : ", accuracy, | |
feed_dict={X : mnist.test.images.reshape(-1, 28, 28, 1), Y : mnist.test.labels}) | |
print("수행시간 : ", '{.3f}'.format(time.time()-start)) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment