# fashion mnist
# 4 layer neural network 구성
import tensorflow as tf
# 데이터 준비
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.fashion_mnist.load_data()
# shape를 조정
x_train = x_train.reshape(-1, 28 * 28)
x_test = x_test.reshape(-1, 28 * 28)
y_train = tf.keras.utils.to_categorical(y_train)
y_test = tf.keras.utils.to_categorical(y_test)
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)
tf.reset_default_graph()
tf.random.set_random_seed(1)
X = tf.placeholder(tf.float32, shape=[None, 784])
Y = tf.placeholder(tf.float32, shape=[None, 10])
kp = tf.placeholder(tf.float32)
# layer 1 만들기
W1 = tf.Variable(tf.random_normal(shape=[784, 256]))
B1 = tf.Variable(tf.random_normal(shape=[256]))
H1 = tf.matmul(X, W1) + B1
H1 = tf.contrib.layers.batch_norm(H1)
H1 = tf.nn.relu(H1)
H1 = tf.nn.dropout(H1, keep_prob=kp)
# H1 shape = [None, 128]
# layer 2 만들기
W2 = tf.Variable(tf.random_normal(shape=[256, 256]))
B2 = tf.Variable(tf.random_normal(shape=[256]))
H2 = tf.matmul(H1, W2) + B2
H2 = tf.contrib.layers.batch_norm(H2)
H2 = tf.nn.relu(H2)
H2 = tf.nn.dropout(H2, keep_prob=kp)
# layer 3
W3 = tf.Variable(tf.random_normal(shape=[256, 128]))
B3 = tf.Variable(tf.random_normal(shape=[128]))
H3 = tf.matmul(H2, W3) + B3
H3 = tf.contrib.layers.batch_norm(H3)
H3 = tf.nn.relu(H3)
H3 = tf.nn.dropout(H3, keep_prob=kp)
# layer 4
W4 = tf.Variable(tf.random_normal(shape=[128, 10]))
B4 = tf.Variable(tf.random_normal(shape=[10]))
# H4 = tf.matmul(H3, W4) + B4
# H4 = tf.nn.relu(H4)
# H4 = tf.nn.dropout(H4, keep_prob=kp)
logit = tf.matmul(H3, W4) + B4
# loss
loss = tf.nn.softmax_cross_entropy_with_logits_v2(logits=logit, labels=Y)
loss = tf.reduce_mean(loss)
pred = tf.nn.softmax(logit)
acc = tf.equal(tf.argmax(pred, axis=1), tf.argmax(Y, axis=1))
acc = tf.reduce_mean(tf.cast(acc, tf.float32))
optimizer = tf.train.AdamOptimizer(0.01).minimize(loss)
# 모델 학습
sess = tf.Session()
sess.run(tf.global_variables_initializer())
epochs = 5
batch = 256
n_batch = len(x_train) // batch
for e in range(epochs):
for b in range(n_batch):
x = x_train[b * batch:(b + 1) * batch]
y = y_train[b * batch:(b + 1) * batch]
sess.run(optimizer, feed_dict={X: x, Y: y, kp: 0.8})
if b % 20 == 0:
print(sess.run([loss, acc], feed_dict={X: x, Y: y, kp: 1.0}))
accuracy = sess.run(acc, feed_dict={X: x_test, Y: y_test, kp: 1.0})
print("{0: .2f}%".format(accuracy * 100))
fashion mnist CNN
- conv1 8장
- pool
- conv2 16장
- pool
- fc
import tensorflow as tf
tf.reset_default_graph()
(x_train, y_train), (x_test, y_test) = \
tf.keras.datasets.cifar10.load_data()
x_train = x_train / 255
x_test = x_test / 255
# X = (X - min) / (max - min)
y_train = tf.keras.utils.to_categorical(y_train)
y_test = tf.keras.utils.to_categorical(y_test)
print(x_train.shape, y_train.shape)
tf.reset_default_graph()
# tf.random.set_random_seed(1)
# conv1 준비
X = tf.placeholder(tf.float32, shape=[None, 32, 32, 3])
Y = tf.placeholder(tf.float32, shape=[None, 10])
W1 = tf.Variable(tf.random_normal(shape=[3, 3, 3, 16]))
B1 = tf.Variable(tf.random_normal(shape=[16]))
H1 = tf.nn.conv2d(X, W1, strides=[1, 1, 1, 1], padding="SAME")
H1 = tf.add(H1, B1)
H1 = tf.contrib.layers.batch_norm(H1)
HR1 = tf.nn.relu(H1)
# pool1
P1 = tf.nn.max_pool(HR1,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding="SAME")
# conv2
W2 = tf.Variable(tf.random_normal(shape=[3, 3, 16, 16]))
B2 = tf.Variable(tf.random_normal(shape=[16]))
H2 = tf.nn.conv2d(P1, W2, strides=[1, 1, 1, 1], padding="SAME")
H2 = tf.add(H2, B2)
H2 = tf.contrib.layers.batch_norm(H2)
HR2 = tf.nn.relu(H2)
# pool2
P2 = tf.nn.max_pool(HR2,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding="SAME")
# flatten
flat = tf.reshape(P2, [-1, 8 * 8 * 16])
# fc layer
W3 = tf.Variable(tf.random_normal(shape=[8 * 8 * 16, 10]))
B3 = tf.Variable(tf.random_normal(shape=[10]))
logit = tf.matmul(flat, W3) + B3
# loss
loss = tf.nn.softmax_cross_entropy_with_logits_v2(
logits=logit, labels=Y)
loss = tf.reduce_mean(loss)
optimizer = tf.train.AdamOptimizer(0.01).minimize(loss)
# acc
pred = tf.nn.softmax(logit)
acc = tf.equal(tf.argmax(pred, axis=1), tf.argmax(Y, axis=1))
acc = tf.reduce_mean(tf.cast(acc, tf.float32))
sess = tf.Session()
sess.run(tf.global_variables_initializer())
epochs = 10
batch = 256
n_batch = len(x_train) // batch
for e in range(epochs):
for b in range(n_batch):
x = x_train[b * batch:(b + 1) * batch]
y = y_train[b * batch:(b + 1) * batch]
sess.run(optimizer, feed_dict={X: x, Y: y})
if b % 20 == 0:
print(sess.run([loss, acc], feed_dict={X: x_train, Y: y_train}))
print("학습평가")
print(sess.run([loss, acc], feed_dict={X: x_test, Y: y_test}))
