dl 분류 기초

04_01_classification.py

import tensorflow as tf
import numpy as np

x_data = np.array([[0, 0], [1, 0], [1, 1], [0, 0], [0, 0], [0, 1]])

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

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

# tf.random_uniform : 정규분포 난수를 생성하는 함수로 배열의 shape, 최소, 최대 값을 파라미터로 받는다.
# -1 ~ 1 사이의 난수를 2x3개 생성한다.
W = tf.Variable(tf.random_uniform([2, 3], -1., 1.))

b = tf.Variable(tf.zeros([3]))

# ex) [1, 0] x [[0.2, 0.3, 0.4] + [0.1, 0.2, 0.3] = [0.3, 0.5, 0.7]
#               [0.1, 0.2, 0.1]]
# 1x2 matmul 2x3 + 1x3 = 1x3
L = tf.add(tf.matmul(X, W), b)

L = tf.nn.relu(L)

model = tf.nn.softmax(L)

cost = tf.reduce_mean(-tf.reduce_sum(Y * tf.log(model), axis=1))
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01)
train_op = optimizer.minimize(cost)

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

for step in range(100):
    sess.run(train_op, feed_dict={X: x_data, Y: y_data})

    if (step + 1) % 10 == 0:
        print(step + 1, sess.run(cost, feed_dict={X: x_data, Y: y_data}))
       
prediction = tf.argmax(model, 1)
target = tf.argmax(Y, 1)
print('예측값:', sess.run(prediction, feed_dict={X: x_data}))
print('실제값:', sess.run(target, feed_dict={Y: y_data}))

is_correct = tf.equal(prediction, target)
print(sess.run(is_correct, feed_dict={X: x_data, Y: y_data}))
print(sess.run(accuracy, feed_dict={X: x_data, Y: y_data})) # 2/6
accuracy = tf.reduce_mean(tf.cast(is_correct, tf.float32))
print('정확도: %.2f' % sess.run(accuracy * 100, feed_dict={X: x_data, Y: y_data}))