티스토리 뷰
Simple CNN을 이용하여 MNIST를 분류해보겠다.
MNIST and Convolutional Neural Network¶
In [1]:
import tensorflow as tf
import random
# Import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
tf.set_random_seed(777) # reproducibility
In [2]:
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# Check out https://www.tensorflow.org/get_started/mnist/beginners for
# more information about the mnist dataset
# hyper parameters
learning_rate = 0.001
training_epochs = 15
batch_size = 100
Conv layer 1¶
input layer ~ convolutional layer1 ~ pooling layer1
In [3]:
# input placeholders
X = tf.placeholder(tf.float32, [None, 784])
X_img = tf.reshape(X, [-1, 28, 28, 1]) # img 28x28x1 (색1개) (black/white)
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)) # 필터의 크기 3x3, 색은 1개, 32개의 필터
# Conv -> (?, 28, 28, 32)
# Pool -> (?, 14, 14, 32) # 2번째 convolution layer의 입력으로 사용
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')
'''
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)
'''
Out[3]:
Conv layer 2¶
convolutional layer2 ~ pooling layer2
In [4]:
# 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_flat = tf.reshape(L2, [-1, 7 * 7 * 64]) # fully connected에 넣기 전에 쭉 펼친다.
'''
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("Reshape_1:0", shape=(?, 3136), dtype=float32)
'''
Out[4]:
Fully Connected (FC, Dense) layer¶
In [5]:
# Final FC 7x7x64 inputs -> 10 outputs
W3 = tf.get_variable("W2", shape=[7 * 7 * 64, 10],
initializer=tf.contrib.layers.xavier_initializer())
b = tf.Variable(tf.random_normal([10]))
logits = tf.matmul(L2_flat, W3) + b
# define cost/loss & optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
Training and Evaluation¶
In [6]:
# initialize
sess = tf.Session()
sess.run(tf.global_variables_initializer())
# train my model
print('Learning started. It takes sometime.')
for epoch in range(training_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)
feed_dict = {X: batch_xs, Y: batch_ys}
c, _ = sess.run([cost, optimizer], feed_dict=feed_dict)
avg_cost += c / total_batch
print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost))
print('Learning Finished!')
# Test model and check accuracy
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print('Accuracy;', sess.run(accuracy, feed_dict={
X: mnist.test.images, Y: mnist.test.labels}))
In [7]:
# Get one and predict
r = random.randint(0, mnist.test.num_examples - 1)
print("Label: ", sess.run(tf.argmax(mnist.test.labels[r:r + 1], 1)))
print("Prediction: ", sess.run(
tf.argmax(logits, 1), feed_dict={X: mnist.test.images[r:r + 1]}))
# plt.imshow(mnist.test.images[r:r + 1].
# reshape(28, 28), cmap='Greys', interpolation='nearest')
# plt.show()
Deep CNN¶
Input layer
-Convolution layer1 -Pooling layer1
-Convolution layer2 -Pooling layer2
-Convolution layer3 -Pooling layer3
-Locally connected layer
-Fully conected layer1 -Fully connected layer2
-Output layer
In [8]:
tf.set_random_seed(777) # reproducibility
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# Check out https://www.tensorflow.org/get_started/mnist/beginners for
# more information about the mnist dataset
# hyper parameters
learning_rate = 0.001
training_epochs = 15
batch_size = 100
# dropout (keep_prob) rate 0.7~0.5 on training, but should be 1 for testing
keep_prob = tf.placeholder(tf.float32)
# input place holders
X = tf.placeholder(tf.float32, [None, 784])
X_img = tf.reshape(X, [-1, 28, 28, 1]) # img 28x28x1 (black/white)
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=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=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=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=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]))
logits = tf.matmul(L4, W5) + b5
'''
Tensor("add_1:0", shape=(?, 10), dtype=float32)
'''
# define cost/loss & optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# initialize
sess = tf.Session()
sess.run(tf.global_variables_initializer())
# train my model
print('Learning started. It takes sometime.')
for epoch in range(training_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)
feed_dict = {X: batch_xs, Y: batch_ys, keep_prob: 0.7} # 학습할 땐 0.7로 test할 땐 1로
c, _ = sess.run([cost, optimizer], feed_dict=feed_dict)
avg_cost += c / total_batch
print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost))
print('Learning Finished!')
# Test model and check accuracy
# if you have a OOM error, please refer to lab-11-X-mnist_deep_cnn_low_memory.py
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print('Accuracy:', sess.run(accuracy, feed_dict={
X: mnist.test.images, Y: mnist.test.labels, keep_prob: 1}))
# Get one and predict
r = random.randint(0, mnist.test.num_examples - 1)
print("Label: ", sess.run(tf.argmax(mnist.test.labels[r:r + 1], 1)))
print("Prediction: ", sess.run(
tf.argmax(logits, 1), feed_dict={X: mnist.test.images[r:r + 1], keep_prob: 1}))
# plt.imshow(mnist.test.images[r:r + 1].
# reshape(28, 28), cmap='Greys', interpolation='nearest')
# plt.show()
Dropout과 layer를 추가했더니 99%가 넘는 정확도가 나왔다.
'beginner > 파이썬 딥러닝 기초' 카테고리의 다른 글
| NN의 꽃 RNN 이야기 (0) | 2019.05.13 |
|---|---|
| Class, tf.layers, Ensemble (MNIST 99.5%) (0) | 2019.05.13 |
| TensorFlow CNN의 기본 (0) | 2019.05.12 |
| ConvNet의 활용 (0) | 2019.05.12 |
| ConvNet Max Pooling (0) | 2019.05.12 |