파이썬의 클래스로 만들어 사용하자. 복잡한 layer를 만들 때 사용하자.
class Model:
def __init__(self, sess, name):
self.sess = sess
self.name = name
self._build_net()
def _build_net(self):
with tf.variable_scope(self.name):
# dropout (keep_prob) rate 0.7~0.5 on training, but should be 1
# for testing
self.keep_prob = tf.placeholder(tf.float32)
# input place holders
self.X = tf.placeholder(tf.float32, [None, 784])
# img 28x28x1 (black/white)
X_img = tf.reshape(self.X, [-1, 28, 28, 1])
self.Y = tf.placeholder(tf.float32, [None, 10])
# L1 ImgIn shape=(?, 28, 28, 1)
W1 = tf.Variable(tf.random_normal([3, 3, 1, 32], stddev=0.01))
# Conv -> (?, 28, 28, 32)
# Pool -> (?, 14, 14, 32)
L1 = tf.nn.conv2d(X_img, 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')
L1 = tf.nn.dropout(L1, keep_prob=self.keep_prob)
'''
Tensor("Conv2D:0", shape=(?, 28, 28, 32), dtype=float32)
Tensor("Relu:0", shape=(?, 28, 28, 32), dtype=float32)
Tensor("MaxPool:0", shape=(?, 14, 14, 32), dtype=float32)
Tensor("dropout/mul:0", shape=(?, 14, 14, 32), dtype=float32)
'''
# L2 ImgIn shape=(?, 14, 14, 32)
W2 = tf.Variable(tf.random_normal([3, 3, 32, 64], stddev=0.01))
# Conv ->(?, 14, 14, 64)
# Pool ->(?, 7, 7, 64)
L2 = tf.nn.conv2d(L1, W2, strides=[1, 1, 1, 1], padding='SAME')
L2 = tf.nn.relu(L2)
L2 = tf.nn.max_pool(L2, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
L2 = tf.nn.dropout(L2, keep_prob=self.keep_prob)
'''
Tensor("Conv2D_1:0", shape=(?, 14, 14, 64), dtype=float32)
Tensor("Relu_1:0", shape=(?, 14, 14, 64), dtype=float32)
Tensor("MaxPool_1:0", shape=(?, 7, 7, 64), dtype=float32)
Tensor("dropout_1/mul:0", shape=(?, 7, 7, 64), dtype=float32)
'''
# L3 ImgIn shape=(?, 7, 7, 64)
W3 = tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=0.01))
# Conv ->(?, 7, 7, 128)
# Pool ->(?, 4, 4, 128)
# Reshape ->(?, 4 * 4 * 128) # Flatten them for FC
L3 = tf.nn.conv2d(L2, W3, strides=[1, 1, 1, 1], padding='SAME')
L3 = tf.nn.relu(L3)
L3 = tf.nn.max_pool(L3, ksize=[1, 2, 2, 1], strides=[
1, 2, 2, 1], padding='SAME')
L3 = tf.nn.dropout(L3, keep_prob=self.keep_prob)
L3_flat = tf.reshape(L3, [-1, 128 * 4 * 4])
'''
Tensor("Conv2D_2:0", shape=(?, 7, 7, 128), dtype=float32)
Tensor("Relu_2:0", shape=(?, 7, 7, 128), dtype=float32)
Tensor("MaxPool_2:0", shape=(?, 4, 4, 128), dtype=float32)
Tensor("dropout_2/mul:0", shape=(?, 4, 4, 128), dtype=float32)
Tensor("Reshape_1:0", shape=(?, 2048), dtype=float32)
'''
# L4 FC 4x4x128 inputs -> 625 outputs
W4 = tf.get_variable("W4", shape=[128 * 4 * 4, 625],
initializer=tf.contrib.layers.xavier_initializer())
b4 = tf.Variable(tf.random_normal([625]))
L4 = tf.nn.relu(tf.matmul(L3_flat, W4) + b4)
L4 = tf.nn.dropout(L4, keep_prob=self.keep_prob)
'''
Tensor("Relu_3:0", shape=(?, 625), dtype=float32)
Tensor("dropout_3/mul:0", shape=(?, 625), dtype=float32)
'''
# L5 Final FC 625 inputs -> 10 outputs
W5 = tf.get_variable("W5", shape=[625, 10],
initializer=tf.contrib.layers.xavier_initializer())
b5 = tf.Variable(tf.random_normal([10]))
self.logits = tf.matmul(L4, W5) + b5
'''
Tensor("add_1:0", shape=(?, 10), dtype=float32)
'''
# define cost/loss & optimizer
self.cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=self.logits, labels=self.Y))
self.optimizer = tf.train.AdamOptimizer(
learning_rate=learning_rate).minimize(self.cost)
correct_prediction = tf.equal(
tf.argmax(self.logits, 1), tf.argmax(self.Y, 1))
self.accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
def predict(self, x_test, keep_prop=1.0):
return self.sess.run(self.logits, feed_dict={self.X: x_test, self.keep_prob: keep_prop})
def get_accuracy(self, x_test, y_test, keep_prop=1.0):
return self.sess.run(self.accuracy, feed_dict={self.X: x_test, self.Y: y_test, self.keep_prob: keep_prop})
def train(self, x_data, y_data, keep_prop=0.7):
return self.sess.run([self.cost, self.optimizer], feed_dict={
self.X: x_data, self.Y: y_data, self.keep_prob: keep_prop})
여러개를 조합해서 조화롭게 만든다. 여러개의 독립된 Model을 training시키고, 각 예측을 조합하여 최종 결과를 만든다.
각각의 합치는 것으로 조화롭게 만들어 본다. 결과 중 가장 높은 값을 선택한다.
Tensorflow 코드에서 prediction은 최종 결과의 값들이다. 정확도가 0.9952 까지 올라간다.
