05.deep_neural_net_Costfun2

review¶

In [1]:

import tensorflow as tf
import numpy as np

In [2]:

# data_define

# data_define
# [털, 날개]
x_data = np.array([
    [0, 0],
    [1, 0],
    [1, 1],
    [0, 0],
    [0, 0],
    [0, 1]
])

# [기타, 포유류, 조류]
y_data = np.array([
    [1, 0, 0], # 기타
    [0, 1, 0], # 포유류
    [0, 0, 1], # 조류
    [1, 0, 0], # 기타
    [1, 0, 0], # 기타
    [0, 0, 1]  # 조류
])

model setting¶

In [3]:

X = tf.placeholder(tf.float32)
Y = tf.placeholder(tf.float32)

W1 = tf.Variable(tf.random_normal([2, 10], mean=0, stddev=1))
W2 = tf.Variable(tf.random_normal([10, 3], mean=0, stddev=1))

b1 = tf.Variable(tf.zeros([10]))
b2 = tf.Variable(tf.zeros([3]))

L1 = tf.add(tf.matmul(X, W1), b1)
L1 = tf.nn.sigmoid(L1)

model = tf.add(tf.matmul(L1, W2), b2)
model = tf.nn.softmax(model)

cost function¶

• one-hot encoding을 이용한 대부분의 모델에서는 cross-entropy를 사용
  $E(w,\quad b)\quad =\quad -\sum _{ n=1 }^{ N } \left\{ { t_{ n }logy_{ n }+(1-t_{ n })log(1-y_{ n }) } \right\} $

In [4]:

cost = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits_v2(labels=Y, logits=model))

modeling¶

In [5]:

optimizier = tf.train.GradientDescentOptimizer(learning_rate=0.01)
train_op = optimizier.minimize(cost)

In [6]:

init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

for step in range(1000):
    sess.run(train_op, feed_dict={X: x_data, Y:y_data})
    
    if (step+1) % 50 == 0:
        print("{}, {:.5f}".format(step+1, sess.run(cost, feed_dict={X: x_data, Y:y_data})))

50, 1.15160
100, 1.14459
150, 1.13681
200, 1.12806
250, 1.11820
300, 1.10710
350, 1.09478
400, 1.08139
450, 1.06730
500, 1.05302
550, 1.03913
600, 1.02610
650, 1.01422
700, 1.00354
750, 0.99399
800, 0.98538
850, 0.97755
900, 0.97032
950, 0.96356
1000, 0.95717

output¶

In [7]:

sess.run(model, feed_dict={X: x_data, Y:y_data})

Out[7]:

array([[0.64512706, 0.08173119, 0.2731418 ],
       [0.37277853, 0.06834452, 0.55887693],
       [0.3646471 , 0.05929578, 0.57605714],
       [0.64512706, 0.08173119, 0.2731418 ],
       [0.64512706, 0.08173116, 0.2731418 ],
       [0.51281446, 0.0757072 , 0.41147828]], dtype=float32)

In [8]:

prediction = tf.argmax(model, axis=1)
target = tf.argmax(Y, axis=1)

print("prediction: \t{}".format(sess.run(prediction, feed_dict={X:x_data})))
print("target: \t{}".format(sess.run(target, feed_dict={Y:y_data})))

prediction: 	[0 2 2 0 0 0]
target: 	[0 1 2 0 0 2]

accuracy¶

In [9]:

is_correct = tf.equal(prediction, target)
accuracy = tf.reduce_mean(tf.cast(is_correct, tf.float32))
print("accuracy: \t{:.3f}".format(sess.run(accuracy, feed_dict={X:x_data, Y:y_data})))

accuracy: 	0.667

In [10]:

from IPython.core.display import display, HTML
display(HTML("<style> .container{width:100% !important;}</style>"))